WO2001029769A9 - Method and apparatus for aligning and comparing images of the face and body from different imagers - Google Patents
Method and apparatus for aligning and comparing images of the face and body from different imagersInfo
- Publication number
- WO2001029769A9 WO2001029769A9 PCT/US2000/041320 US0041320W WO0129769A9 WO 2001029769 A9 WO2001029769 A9 WO 2001029769A9 US 0041320 W US0041320 W US 0041320W WO 0129769 A9 WO0129769 A9 WO 0129769A9
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- minutiae
- image
- images
- infrared
- face
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/41—Detecting, measuring or recording for evaluating the immune or lymphatic systems
- A61B5/414—Evaluating particular organs or parts of the immune or lymphatic systems
- A61B5/415—Evaluating particular organs or parts of the immune or lymphatic systems the glands, e.g. tonsils, adenoids or thymus
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/117—Identification of persons
- A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
- A61B5/1176—Recognition of faces
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/41—Detecting, measuring or recording for evaluating the immune or lymphatic systems
- A61B5/414—Evaluating particular organs or parts of the immune or lymphatic systems
- A61B5/418—Evaluating particular organs or parts of the immune or lymphatic systems lymph vessels, ducts or nodes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Definitions
- IR infrared
- visual images of the human body.
- head shape and size, and the relative location, shape, and size of features such as the eyes, mouth, and nostrils are the same in both imaging modes.
- a database of images can be segmented into classes using metrics derived from those common features, and the same classification will be obtained from either visual or infrared images. Height can be also used as a classification measure when it can be inferred from the collected image or from separate sensor data.
- An infrared image of an unclothed area of the body, such as the face presents much more detailed and person-specific information than does a visible image.
- visible images are more commonly collected and large historical databases of visual images exist. It is therefore desirable to automate a process for comparing imagery from both the visual and infrared modes.
- Infrared images are unique to each person, even for identical twins. Visual images are not unique because many people look similar and can disguise themselves to look enough like one another that an automated identification system cannot distinguish them. Therefore, in a large database, it is not possible to automatically perform a one-to-one linkage between infrared and visual images because the visual images are not sufficiently unique. However, for each infrared image, an automated system can eliminate all visual images which cannot be a match due to insufficient correspondence between minutiae characteristics. In general, it is estimated that more than 95% of a visual database can be eliminated as a match to a given infrared image. This has application to the use of infrared surveillance cameras to identify wanted persons for whom only visual images are on file.
- the infrared- visual matching system compares each person it sees in infrared and classifies him as either a possible match to someone on the visual image watch list or not a match. Persons who are possible matches can then receive greater attention from immigration or security authorities. This allows the use of infrared surveillance imagery to proceed without waiting until a large database of infrared images is established.
- infrared imagery also provides for the detection of disguises, whether worn or surgical, which may not be detectable from visible imagery.
- artificial facial hair such as a mustache is readily detectable in an infrared image although it appears natural in visible images.
- infrared surveillance imagery shows a man with a fake mustache provides a clue to consider in matching against a visible image database.
- Surgical disguises such as a face lift leave telltale short and longer term variations in the facial thermogram, while the visual image may appear to be a different person and show no sign of surgery.
- the ability to detect in IR images that surgical changes have been made to a particular area of the face permits an automated system to broaden the parameters for searching for possible matching visual images in an historical database.
- High definition visual images of the face and body are routinely produced and stored for medical, diagnostic and forensic use. Common examples are the photographing of criminal suspects through booking stations producing "mug shots”, driver's license photographs produced by each state, and passport photos used by the State Department.
- Regions of Interest may be utilized instead of minutiae, where the ROI may be elemental or other shapes including fractal or wavelet-derived structures, segments of blood vessels, locations underneath or otherwise relative to tattoos, moles, freckles, or other distinguishable features, or wiremesh or finite elements used for thermodynamic or visible modeling of the body. Rules may relate the shapes and positions of such elements, their centroids and other features. Time sequences of minutiae and ROIs may be compared, with the decision as to a possible match made on the basis of cumulative thresholds and rule tolerances over the sequence. Facial expression and speech modeling has application to synthetic videoconferencing and face animation. Substantial bandwidth and storage reduction can result. Use of IR minutiae offers more precise modeling than current use of visual images.
- the present invention provides a technique by which IR images can be tied to the visual image being displayed.
- the comparison of thermal minutiae from two facial images is analogous to the comparison of sets of fingerprint minutiae, in that two images are said to identify the same person if a significant subset of the two sets are found to correspond sufficiently in relative positions and characteristics.
- Classification of the facial thermograms can be performed to partition a database and reduce the search for matching facial patterns.
- encoding of the minutiae patterns offers a unique FaceCode which may be repeatably derived from each person, minimizing the need for searching a database.
- Infrared imaging can be used to locate minutiae points over the entire body surface which correspond to specific anatomical locations such as intersection points and branch points of the underlying blood vessels.
- the thermal minutiae technique and apparatus utilizes a built-in set of whole-body registration points viewable in IR on the face and body surface.
- the registration points can then be used to compare infrared images taken with different equipment at different times of different people and under different conditions to facilitate comparison of those images.
- the IR camera is totally passive, emitting no energy or other radiation of its own, but merely collecting and focusing the thermal radiation spontaneously and continuously emitted from the surface of the human body.
- Current IR cameras operating in the mid to long wavelength region of 3-12 microns, record patterns caused by superficial blood vessels which lay up to 4 cm below the skin surface. Future cameras will have increased sensitivity which will translate into even more defined minutiae.
- approximately 175 thermal facial minutiae may be identified in thermal images from superficial blood vessels in the face. More than 1000 thermal minutiae may be identified over the whole body surface. Using more sensitive infrared cameras, additional minutiae from deeper vascular structures may be identified in the thermal images.
- the normal body is basically thermally bilaterally symmetric.
- the technique for thermal minutiae extraction and matching can be summarized as follows: 1.
- the current thermal image is digitized.
- the current image is divided into pixels, where the size of the pixel relates to the resolution or quality of the result desired
- Each minutia is assigned characteristics such as one or more vectors having magnitude and directional information in relation to the surrounding areas of the thermal image about that minutia, absolute or relative temperature at or around the minutia location, shape of the surrounding thermal area or areas, curvature of the related shape or shapes, size of the surrounding shape or shapes, location of the minutia relative to the body, distance to other minutiae, vector length and direction to other minutiae, number of crossings of thermal contours between it and other minutiae, number of other minutiae within a certain range and direction, the type of minutiae such as the apparent end point of a blood vessel, a point of maximum curvature of a thermal contour, all points on an anatomical element such as a blood vessel which can be distinguished by thresholding or range gating or focusing the thermal camera or image, the centroid of a lymph node, or the centroid or other reference of an anatomical structure with distinguishing thermal capacitance.
- characteristics such as one or more vectors having magnitude and directional information in
- Either active or passive infrared imaging can be used.
- active imaging the subject can be subjected to heat or cold by external application of hot or cold air, illumination, dehumidification, ingestion of hot or cold foodstuffs, or ingestion of materials which cause vasodilation or vasoconstriction.
- a set of minutiae characteristics of the current image is compared by computer to the set of minutiae characteristics of other images.
- the comparison results are used to determine corresponding minutiae from the two images, and to morph or mathematically adjust one image with respect to the other to facilitate comparison.
- Infrared facial minutiae may be derived from elemental shapes (such as by using the centroids of each shape or the zero locations resulting from wavelet compression and expansion). Particularly when high quality infrared images are used, absolute minutiae can be directly extracted without the computationally intensive analysis required for template or shape comparisons.
- the Tal U.S. patent No. 4,975,969 discloses a method and apparatus for uniquely identifying individuals by measurement of particular physical characteristics viewable by the naked eye or by imaging in the visible spectrum.
- Tal defined facial parameters which are the distances between identifiable parameters on the human face, and/or ratios of the facial parameters, and used them to identify an individual since he claims that the set of parameters for each individual is unique.
- Particular parameters such as the distance between the eye retina, the distance from each eye retina to the nose bottom and to the mouth center, and the distance from the nose bottom to the mouth center are set forth, as they may be particularly defined due to the shadowed definable points at each end.
- the approach disclosed in the Tal patent utilizes visible features on the face from which a unique set of measurements and ratios allegedly can be developed for each individual. This approach is not particularly satisfactory, nor does it pertain to identical twins.
- the "rubber sheeting" effect caused by changes in facial expression the aging effects which cause lengthening of the nose, thinning of the lips, wrinkles, and deepening of the creases on the sides of the nose, would all cause changes in the parameters and in their ratios. Therefore, very few measurements which can be made on a human face are constant over time, and the paucity of such constant measurements makes it improbable that facial metrics in visible images can be useful for identification of sizable populations.
- the Tal patent does not deal with comparison of images from other than visible detectors, and so does not consider the specific focus of the present invention which is the comparison of images from different spectral bands. Moreover, the Tal patent does not specifically caution about varying lighting conditions, which could severely limit the utility of the technique, even for classification.
- Visible face metrics may be useful as a classification technique, but the visible features can be modified cosmetically or surgically without detection, resulting in mis- classification.
- the technique of the present invention utilizes hidden micro parameters which lie below the skin surface, and which cannot be forged.
- the current patent's use of underlying features which are fixed into the face at birth and remain relatively unaffected by aging provides for less inherent variability in the values of the parameters over time than is provided by the prior art.
- Visible metrics require ground truth distance measurements unless they rely strictly upon ratios of measurements. They can be fooled by intentional disguises, and they are subject to variations caused by facial expressions, makeup, sunburns, shadows and similar unintentional disguises. Detecting disguises and distinguishing between identical twins may or may not be possible from visible imagery if sufficient resolution and controlled lighting is available. However, the level of resolution which may be required significantly increases the computational complexity of the identification task, and makes the recognition accuracy vulnerable to unintentional normal variations.
- Pentland MCT Media Laboratory Perceptual Computing Section, Technical Report No. 245 View-Based and Modular Eigenspaces for Face Recognition. Faces are then described in terms of weighting of those features.
- a representative sample of 128 faces was used from a database of 7,562 images of approximately 3000 people.
- a principal components analysis was performed on a representative sample. The first 20 eigenvectors were used. Each image was annotated by hand as to sex, race, approximate age, facial expression, etc. Pentland does not deal with comparing images from different spectral bands. Nor does his technique perform well in the case of visible images obtained under differing lighting conditions.
- Pentland discloses that pre-processing for registration is essential to eigenvector recognition systems.
- the processing required to establish the eigenvector set is extensive, especially for large databases. Addition of new faces to the database requires the re- running of the eigenanalysis. Pentland and other "eigenface" approaches are database- dependent and computationally intensive.
- the proposed minutiae comparison of the present invention is independent of the database context of any two images. Minutiae are directly derived from each image, visible or IR, and compared using fixed rules, regardless of the number or content of other images in the database.
- Applicant has previously utilized a principal components analysis of thermal shapes found in facial thermograms. The resulting accuracy of 97% from IR images equals or su ⁇ asses the results reported by Pentland with visible facial images. Applicant's training database, furthermore, included identical twins and involved non-cooperative imaging of about 200 persons. Thus, the head sizes and orientations were not pre-determined as they were in the Pentland study. As a result, the use of eigenanalysis of thermal shapes is more robust than the use of eigenanalysis of visual facial features. However, the basic requirements of eigenanalysis still pertain to their use in matching of thermal images by consideration of inherent elemental shapes. That is, the approach is computationally intensive, requires a pre-formed database, and requires standardization of the images through pre-processing.
- the present invention differs from prior visible and IR recognition approaches in that it does not merely sample a finite number of points on an image grid; it extracts points which have particular meaning in each spectrum and automatically distinguishes between cross-spectrum minutiae which are coincident and those which are related by rules associated with anatomical bases. It assigns a difference or feature space distance to each pair of coincident minutiae, with a total distance calculated over all such pairs. This first step may be used to eliminate candidate matches which produce distances above a threshold. Then the spectrum-dependent minutiae are compared relative to anatomical rules to further eliminate impossible candidate matches.
- the prior art has not addressed alignment and comparison of visual/IR or IR/TR human images based upon anatomical rules and the characteristics of features viewable in the ER image.
- a thermal image of a portion of the individual's body is generated and is processed to produce a set of minutiae points, together with characteristics which describe each such point and its relation to other minutiae. That combination of minutiae and characteristics is considered unique to the individual and essentially persistent in spite of ambient, physiological, emotional, and other variations which occur on a daily basis. Any portion of the body can be utilized, but the face is preferred due to its availability.
- the system and method allows for identification based on partial faces.
- Candidate visual images are processed to extract minutiae characteristic of the subject and the visual spectrum.
- the IR and visual images are scaled to the same standard and aligned based upon minutiae which are coincident in the two spectra.
- a measure of the amount of warping required to accomplish the alignment is calculated.
- other spectrum-dependent minutiae are compared, with relation to certain rules which would be met if the two images were of the same person, based upon anatomical structures of the human face and body.
- a measure of the degree of compliance with the rules is calculated.
- the decision to include or exclude a given visual image from the class of possible matching images to the infrared image is made based upon these measures relative to thresholds which are established to control possible errors in the system.
- establishing axes for the facial minutiae is also essential.
- human operators establish face axes, similar to finge ⁇ rint examiners setting the orientation of latents.
- a human demarcates the eye pupils, canthi and/or nostrils by manipulating a cursor on the system display.
- Axes are then automatically generated vertically through the center of mass of the eye pupils or canthi and nostrils and horizontally through the pupils or canthi centroids.
- the vertical axis can be adjusted to not necessarily bisect the nostrils.
- the human operator also indicates any unusual features, such as a missing eye or eye patch, wearing of bandages, tattoos, deformation of the lips or other visible gross thermal asymmetries of the face.
- An automated system can perform these as well.
- the unknown face is partitioned into segments, and corresponding segments matched. This will accommodate matching of partial faces when faces are partially disguised or hidden behind other faces in a crowd.
- the thermal image is grossly symmetrical bilaterally.
- the canthi or sinus areas in normal individuals are the hottest extended areas of the face.
- Other features which may be used are the nostrils, which may present alternately hot and cold bilaterally symmetric areas as the individual breathes in and out.
- the horizontal axis may be drawn through the outer corners of each eye, which are readily distinguishable in the infrared images or through the pupils which may be seen in some IR imagery.
- the vertical axis may then be drawn through the bow of the upper lip, or through the center point of the two nostrils, or at the midpoint between the eye corners.
- the intersection of the two axes will occur at the center of the two eyes.
- the midpoint between the horizontal through the eyes is defined as the center of the face.
- the pattern of the glasses which block the infrared emissions from the face and thereby produce an extended cold area with sha ⁇ cut-off thermally, can be used to approximate the facial axes.
- a sufficient number of minutiae are obtainable from portions of the face not blocked by glasses, facial hair, or other concealments, a person maybe identifiable.
- fewer than a minimum number of minutiae specified for a particular scenario are extracted by an automated system for a particular person, that person may be considered by the system to be a potential match, but be tagged as having a low number of minutiae.
- minutiae matching algorithms allow for variations in the position and characteristics of the minutiae, as well as in the subset of minutiae which are seen due to the field of view of the camera and to possible obstruction of certain areas of the face in the image.
- the face surface presents a smooth continuum of thermal levels, and reflects metabolic activity, ambient and internal temperatures, and ambient sources of thermal energy. Discontinuities occur at breaks in the skin continuum, such as caused by the nostrils, the mouth opening, the eyes, facial hair, moles or other skin disturbances, and any applique such as bandages.
- minutiae are used from the face.
- the minutiae are referenced to axes derived from specific physiological features.
- many different approaches may be used to obtain repeatable minutiae from facial thermograms, the preferred approach uses a number of extraction routines to produce a plurality of minutiae sufficient for an intended pu ⁇ ose.
- on the order of ten minutiae may be extracted using absolute anatomical positions such as branch locations of the carotid and facial arteries.
- on the order of 100 derived minutiae may be extracted using additional computations to identify further derived and absolute minutiae.
- the minutiae extraction and characterization procedure locates the position of each minutia.
- characteristics of each point such as: a vector indicating the orientation of the corresponding blood vessel; a second vector indicating the relative orientation of the branching blood vessel; the normalized apparent temperature; and the apparent width of the corresponding blood vessels.
- use of the characteristics can enhance the speed and accuracy of identification.
- it can improve the accuracy and speed of automatic fusion of medical imagery.
- This basic technique can be employed on an area-by-area basis when portions of the body cannot be seen or when significant changes have occurred in portions of the thermogram such as when portions of the body have suffered external wounds.
- thermogram This would be done by segmenting the thermogram to consider only the portions of the body in which minutiae can be detected. Functionally this is equivalent to matching a latent partial finge ⁇ rint found at a crime scene to a full rolled print filed in the FBI system.
- the set of minutiae points, together with characteristics which describe each such point and its relation to other minutiae is considered unique to the individual and persistent, for both contact finge ⁇ rints and thermal minutiae.
- Verification that two images from different spectra may be from the same person can be an end goal in itself or the first step in further processing the two images to extract comparison data.
- a change in facial expression or the action of speech causes movements in affected areas of the face, particularly the lips, but also the eye, chin, forehead, and cheek areas.
- Encoding of facial expressions and facial movements during speech is currently being studied for bandwidth reduction in the transmission of "talking head" video for applications such as videophone, videoconferencing, video email, synthetic speech, and face animation.
- the intent is to transmit a baseline image followed by encoded changes to that image, with reconstruction of the animated face at the receiving end. This process offers significant bandwidth reduction, but may produce imagery in which the talking face seems stiff and unnatural or does not appear to be synchronized with the audio, giving the unacceptable look of a dubbed foreign film.
- Infrared minutiae are more numerous than visible markers and are present throughout the face, including areas of the cheeks and forehead and chin where no visible minutiae may be present. Therefore, modeling of the movements of infrared minutiae can provide finer detailed replication of expressions and speech than modeling based upon visual references.
- a visual baseline image of the subject face is sent, followed by transmission of only the movement vectors of those infrared minutiae which move from frame to frame.
- the baseline face is animated based upon overlaying the IR minutiae movements on the visual image.
- Video e-mail and videophone could also utilize the significant bandwidth reduction and automated re-synchronization of voice and image.
- a sequence of movements of infrared minutiae can be extracted which corresponds to that expression or speech element for that person or for persons in general. Subsequently, when the same sequence of movements of infrared minutiae is seen, it can be inferred that the person is displaying the same expression or speech element as during the initial sequence.
- This enables the automated determination of expression or speech, allowing for compression of transmitted video in conjunction with audio.
- the combination may offer additional composite compression and improved synchronization.
- the same basic technique can also be used to create a dictionary of facial expressions and speech elements for use in animation of a synthetic face.
- the talking head video compression system will have both video and IR cameras, and can be used to recognize and/or generate facial expressions and/or speech-related facial movements from the IR image and superimpose them on a contemporaneous visual image.
- the use of correlated infrared and video facial images offers significantly better fidelity of expression and speech-related variations in compression and reconstruction of talking head video, while also ensuring the authenticity of the related transmissions.
- FIGURES Figs, la and lb are a visual image and facial thermogram, respectively, taken of the same face from a distance of 15 feet showing coincident minutiae for each modality
- Figs 2a - 2d are visual images of four different faces, respectively, showing coincident minutiae
- Figs. 3a - 3d are image of the vascular structure and feature images from infrared minutiae of the visual images of Figs, la, 2a, and 2b, respectively, generated by thresholding the IR image and using all pixels hotter than threshold;
- Fig.4 is an infrared image of an individual with a scar which is not detectable in a visible image owing to make-up on the individual;
- Fig. 5a illustrates an overlay of the IR image of Fig. 3a onto the corresponding visual image of Fig. la to illustrate the alignment of coincident minutiae;
- Fig. 5b illustrates an overlay of the ER image of Fig. 3b onto the visual image of Fig. la to illustrate the misalignment of coincident minutiae;
- Figs.6a - 6c are thresholded infrared images of the frontal face, side face, and neck, respectively, of an individual taken with an indium antimonide focal plane array camera;
- Figs. 7a and 7b are images of vascular structure minutiae for an individual smiling and frowning, respectively;
- Fig. 8 is a flow diagram showing the method according to the invention
- Figs. 9a and 9b are illustrations of two different visual images overlaid with a thermal image of vascular minutiae showing a match and mismatch, respectively
- Fig. 10 is a block diagram showing the apparatus according to the invention.
- the vascular system supplying the human face typically exhibits thermal variations on the order of 7°C across the facial surface.
- Certain general features, such as hot patches in the sinus areas, relatively cool cheeks, and cold hair pertain to all facial thermograms.
- Other features such as specific thermal shapes in certain areas of the face are characteristic of a particular person.
- Variations in temperature across the facial surface can be imaged by thermal cameras sensitive to wavelengths in the 3-5, 8-12, or 2-15 micron ranges.
- Current commercially available cameras provide thermal resolution of 0.025°C and spatial resolution of better than .02", resulting in 65,000 to 265,000 discrete thermal measurements across the surface of the face.
- the thermal map is regenerated 30 times per second to produce either a standard video output which can then be recorded and processed on standard videotape equipment, or a direct digital signal which can be input to a computer.
- Figs, la and lb there are shown the visible and infrared images of the same individual taken via a conventional camera and an infrared camera, respectively. These images contain minutiae 2.
- Figs. 2a-2d are visual images of different people, each image having identifiable minutiae points 2.
- Figs. 3a-3c are thermal or infrared images of the individuals shown in Figs, la, 2a, and 2b.
- minutiae In addition to branch points of superficial blood vessels, various other types of minutiae may be automatically extracted, including: (1) the centroid of each constant thermal area;
- lymph nodes, glands, other anatomical areas of distinguishable thermal capacitance (4) lymph nodes, glands, other anatomical areas of distinguishable thermal capacitance; (5) head outline and hairlines;
- every pixel in an ER image represents a thermal measurement of the skin at that corresponding location on the body
- every pixel in an IR image can be considered a minutia.
- thresholding an IR image and considering all hotter points to be minutiae leads to a simple realization of the preferred embodiment of the invention.
- the methods according to the invention are the same whether the analysis is done more at the minutiae-extraction stage or at the minutiae comparison stage.
- the Tal patent No. 4,975,969 discloses such a method for identifying faces based upon a limited number of measurements between visible features such as the ends of the mouth and ratios between those measurements. According to Tal, no two persons have the same set of such measurements. However, variations in such measurements for a given individual at different times appear to often be larger than the variations between persons. Positive identification of individuals, especially when one individual is attempting to appear to be another, requires the matching of a greater number of minutiae points than are available in the video image. For high security applications, it is desirable that the number of minutiae points extracted be such that it is virtually impossible to locate two individuals who would have identical minutiae sets.
- Scars 4, tattoos, and other marks which are visible in photographs should be selected as shown in Fig. 4. All related pixels can be used as visible minutiae, or a procedure can be established wherein certain features, such as the centroid, or outline, are selected as representative minutiae.
- the infrared image will in general contain more details than will the visible image. Particularly when the visible image is not high resolution, the ER image can be used to distinguish between brands and tattoos and temporary marks better than can a photograph. When makeup is worn, there may be no apparent visible mark.
- the face axes are located. Overlaying the two sets of axes provides the initial approximate correspondence between two different images. In the full-frontal face, the thermal image is grossly symmetrical bilaterally. The canthi or sinus areas in normal individuals are the hottest extended areas of the face. When glasses are not worn, it is normally a simple process to locate the canthi in the thermal image and use them to establish axes for the face.
- the nostrils which may present alternately hot and cold bilaterally symmetric areas as the individual breathes in and out.
- the horizontal axis is drawn through the pupils or canthi, which are readily distinguishable in the infrared images.
- the vertical axis is then drawn through the bow of the upper lip, or through the center point of the two nostrils, to the midpoint between the eyes. The intersection of the two axes occurs at the center of the two eyes which is defined as the center of the face.
- Axes for the visible face images are similarly drawn. Axes can be forced to be pe ⁇ endicular. However, many people have an eyeline which is not pe ⁇ endicular to the vertical axis of their head. Allowing the axes to vary in relative orientation preserves a useful identifying characteristic.
- Infrared minutiae are categorized as absolute if they are directly extractable from the thermal image, and derived if they result from some level of image transformation. Visible minutiae are all assumed to be absolute. Methods for their extraction are set forth below. Other methods may be used within the scope of this invention.
- Infrared minutiae are selected.
- the number of minutiae obtained is a function of the sensitivity and resolution of the infrared camera.
- Candidate minutiae include:
- Absolute minutiae directly extractable from the thermal image, such as: head outline, hairlines, branch points, and apparent end points of the superficial blood vessels.
- the digitized thermal image has N bits of grey scale, begin by dividing the image into two slices (thresholding) about the average grey value. The resulting image will have some number of areas of constant value. Locate the centroid of each, which is labeled as a minutiae point.
- the minutiae set consists of the centroids labeled as (x, y, z) where (x,y) is the location on the face relative to the face axes with (0,0) at the designated face center, and z is the corresponding thermal value.
- B the points of maximum curvature on constant thermal contours, either concave or convex cusps having less than a given radius of curvature.
- the added minutiae set will consist of the maximum inflection points labeled as (x, y, z, a, D), where (x, y) is the location of the minutia point relative to the facial axes, z is the thermal value at that point, a is the angle subtended by a tangent to the thermal contour at the minutia point, and D is the range of thermal values (equal to the number of constant thermal contours crossed) between the minutia point and the centroid of its thermal contour.
- C run length encoding start and stop locations.
- Each stop/start location generates a minutia point.
- the added minutiae set will consist of the (x, y, z) value associated with those points.
- D undefined locations generated by compression and subsequent expansion.
- the added minutiae set will consist of the undefined locations and will be labeled as (x, y, z,w) where (x,y) is the location of the point relative to the facial axes, z is the thermal value at that location in the original thermal image, and w is a set of wavelet coefficients.
- Visible minutiae are selected depending on the resolution, contrast, and clarity of the visible images.
- Candidate minutiae include: head outline, hairlines, pupils, eye inner and outer corners, nostrils, mouth corners, lip bow, and tip of nose.
- Tables are then created of the infrared minutiae and the visible minutiae.
- Table entries include the locations of each minutiae relative to the face axes.
- Coincident minutiae are linked either manually or automatically.
- Coincident minutiae include: pupils, inner and outer eye corners, nostrils, head outline, hairlines, and ear - head connection points.
- One such method is standard graph matching, with tolerances established for errors due to imperfect knowledge of head position and distance, and errors associated with treating the head/face as a two-dimensional surface or as a sphere, and errors associated with residual errors even if a true three-dimensional model of the head is made, using laser interferometry or other techniques.
- Flash Correlation® as described in the Prokoski U.S. patent No. 5,583,950. Large circular areas at each minutiae location are used, where the size of the area or dot represents the uncertainty associated with the exact minutiae location, due to facial expression changes, camera resolution, and other factors.
- a further method for evaluating the difference between two sets of minutiae is analogous to finge ⁇ rint minutiae, using any of the many minutiae comparison techniques developed to compare location and characteristics of sets of minutiae.
- Figs. 5a and 5b matching of coincident minutiae is illustrated. More particularly, in Fig. 5a, the infrared image of Fig. 3a is overlaid onto the corresponding visual image of Fig. la to illustrate the alignment of coincident minutiae and thus a match of individuals. In Fig. 5b, the infrared image of Fig. 3b is overlaid onto the visual image of Fig. la to illustrate the misalignment of coincident minutiae, thus indicating no match of the individuals.
- the matching algorithm considers such possible variations in deciding possible matches.
- CM CM
- each spectrum-dependent minutiae is considered relative to a rule which relates it to the other image.
- the rule also assigns a point value to the degree of compliance with the rule.
- the system confirms adherence or violation of the rules and computes the cumulative score associated with all of the rules.
- An Exclusion Test is the simplest rule. It states that no vascular structure or minutiae seen in the ER image can be overlaid outside the head outline of the visual image, or inside of the eye, mouth or nostril areas.
- Anatomical rules including the following:
- the facial vein and the facial artery must lie outside nose boundaries, must not go through mouth or eyes or nostrils, and must be inside the face from the ears; 2. the supraorbital and opthalmic arteries must lie above the eyes;
- the transverse vein must lie inside face area between the eyes, and outside the area of the nose;
- the labial vein and artery must surround the mouth.
- a particular class of problems which is of interest includes images taken over long periods of time, whether of children or adults. In these cases, the set of coincident minutiae and the rules governing spectrum-dependent minutiae will vary to accommodate anatomical changes associated with growth and aging. Either of the images being compared may be artificially aged to the other, prior to minutiae being extracted for comparison.
- a threshold is set or determined adaptively, such that pairs of images having a calculated value within the threshold are considered to be possible matches.
- the decision algorithm utilizes a cumulative rule score or simply exclude any image which breaks any rule. The quality of the imagery used, and the possibility of disguise will be considered in establishing the decision algorithm to determine possible or impossible matches.
- Figs.6a- 6c show the threshold infrared image of the front face, side face, and neck of an individual. Two alternative embodiments of the method for aligning and comparing images of the face and body from different images according to the invention will now be described.
- a dualband ER visual camera For compression of talking head video, a dualband ER visual camera is used.
- the processor at the transmitting end continuously extracts ER minutiae from each frame of the
- IR video locates and tracks the face axes, detecting when there is significant head movement.
- a visual baseline image of the subject is sent, followed by transmission of only the movement vectors of those infrared minutiae which move from frame to frame. If significant head movement occurs, then a new baseline video image is transmitted, followed again by transmission sequences of only the movement vectors.
- the baseline face is animated based upon overlaying the ER minutiae movements on the visual image.
- Mo ⁇ hing techniques are used to smooth the transition to a new baseline image. If the mo ⁇ hing indicates too much change in the new baseline, then a signal is sent back to the transmission end to reduce the allowed head movement before a new baseline is transmitted.
- the technique allows for greater bandwidth compression for talking heads with little movement, while allowing automated accommodation of very mobile faces. Separate IR and visual cameras can be used, but the processing time required is greater. Muscles of the face involved in facial expression and speech are shown in Figs 7a and 7b.
- a sequence of movements of infrared minutiae can be extracted which corresponds to that expression or speech element for that person.
- the person is displaying the same expression or speech element as during the initial sequence.
- This enables the automated determination of expression or speech, allowing for compression of transmitted video.
- a baseline image of the person can be transmitted, and then a code for the expression or speech element is transmitted.
- the expression or speech element is reconstructed and a simulated animation of the face presented.
- This technique can also be used to create a dictionary of facial expressions and speech elements for use in animation of a synthetic face.
- a database of images of known individuals is generated 6.
- the images can include infrared, visual, hyperspectral images, or medical images which have been annotated with infrared minutiae. Each image is scaled to a common reference.
- the images in the database are processed for spectrum-dependent features and minutiae 8.
- the processing locates ER minutiae annotated onto other sensor images, assigns face axes, counts the number of minutiae, tags the image with the resulting data, and assigns a quality measure to the image based on the number of minutiae identified and the quality thereof based on the minutiae extraction process.
- selected images of a threshold quality are stored.
- the image of an unknown individual is captured 12 using an infrared camera or other sensor. This image is processed 14 to locate the face axes, scale the image, locate TR minutiae, and assign a quality measure similar to the process step 8.
- the captured image is classified 16 as is the database image 18 to reduce search time.
- Appropriate classification techniques include the use of principal component parameters or symmetry waveforms when both captured and reference databases include only IR images; coincident minutiae metrics when both databases include only ER and visual images; or IR minutiae metrics when both databases include images annotated with ER minutiae. Specific application of a classification technique will depend on the size of the database. Using distance metrics computed from coincident ER and visual minutiae, for example, twelve measurements may be taken which are the same in both ER and visual images. Very large databases can be partitioned effectively using such metrics.
- the classified captured image and the database images are compared to select a potential match 20 from the database. If no potential matches are found, this is the end result. However, if a potential match is found, further processing occurs to verify a match.
- the captured image is positioned 22 to determine the rotation, tip and tilt thereof.
- the database image is similarly positioned 24. If necessary, corrections in position are made so that the images to be compared are similarly oriented.
- the captured and database images are overlaid in alignment 26. This is shown in Figs. 9a and 9b. The distances between coincident minutiae (those which occur in both image modes) are calculated. For each minutiae area of the face, an error band is established which represents the possible variation in position of that minutiae due to facial expression change or speech-related movement.
- Those pairs of coincident minutiae where the captured and database images' minutiae are both within the error band of the other are counted 28.
- the count is compared to a pre-established threshold. If the count is below the threshold, that database image is not considered a possible match and the next sequential image from the database is selected 20 for comparison. If the count is equal to or greater than the threshold, the process continues.
- the composite distance between pairs of coincident minutiae are measured and compared to a pre-determined threshold 30. If the measure is greater than the threshold, that database image is not considered a possible match and the next sequential image from the database is selected 20 for comparison. If the measure is equal to or less than the threshold, the process continues.
- an exclusion zone for the database image is established 32 in which the eyes, nostrils, mouth, and outside boundaries of the face are set as exclusion zones to form a mask of the database image.
- the mask is aligned with and superimposed on the captured image. If any TR minutiae in the captured image fall within the exclusion zones, it is considered a violation, and that database image is no longer considered a possible match and the next image is selected. If no violations occur, the process continues with testing for anatomical rules 34 governing where specific ER minutiae may be located. Those rules are tested against the database images using the captured image. For example, the facial artery must lie between the nose and the ear. When the captured and database images are aligned and overlaid, each anatomical rule is tested.
- a candidate list is created 36.
- the results are weighed 38 in accordance with certain factors such as the database size and completeness. For example, if the database in known to include several images of all employees of a company, that fact will influence the reliability of a match when multiple database images of the same person are found as possible matches to the captured image.
- the candidate matching images from the database are ranked 40 and output 42.
- the apparatus includes a digital storage device 44 for the capture of infrared images. Connected therewith is a standardization processor 46 which standardizes the image and a minutiae processor 48 which extracts and analyzes minutiae for each ER image.
- the apparatus also includes a digital database 50 which stores a plurality of reference images.
- a standardization processor 52 standardizes the images which are delivered to a database 54 containing standardized reference images.
- the minutiae processor 48 for the captured image and the minutiae processor for the database image are connected with a selector comparator device 58 which determines whether a match exists between the images to identify the individual from which the captured image was taken. More particularly, the selector aligns the images to determine if there is an initial match. If not, the comparator compares the coincident minutiae within the images. A first comparison is made by counting the number of coincident minutiae. If the number exceeds a predetermined threshold, the processing continues. If the threshold count is not reached, then the database image is rejected and the next image in the database is selected for comparison. A second comparison is made of the measured distance between coincident minutiae. If the distance exceeds a threshold, the database image is rejected and the next database image is selected for comparison. If the measured distance is below the threshold, processing continues.
- An evaluator 60 tests the database image for exclusion zones and anatomical rules. If any minutiae of the captured image fall within the exclusion zone, a violation occurs and the database image is rejected.
- the anatomical rules specify where specific infrared minutiae may be located. When the captured and database images are overlaid and aligned, each anatomical rule is tested. If a violation occurs, the database image is rejected.
- the database images which pass through the comparison and evaluation stages are weighed according to the strength of match .
- the ranked potential matches are then output through the output device 62.
- the method and apparatus of the invention can be extended to the comparison of images other than visual images such as, for example x-rays or sonograms.
- the x-ray and sonogram images can be aligned by first annotating each with coincident ER minutiae, then mo ⁇ hing the two sets of IR minutiae as overlays onto the medical images, or mo ⁇ hing each medical image to a standard TR image.
- the mo ⁇ hing can be in three dimensions when depth information is provided for the ER minutiae.
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP00986798A EP1194893A4 (en) | 1999-10-21 | 2000-10-20 | Method and apparatus for aligning and comparing images of the face and body from different imagers |
CA002354594A CA2354594A1 (en) | 1999-10-21 | 2000-10-20 | Method and apparatus for aligning and comparing images of the face and body from different imagers |
JP2001532489A JP2003512684A (en) | 1999-10-21 | 2000-10-20 | Method and apparatus for aligning and comparing face and body images from different imagers |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/422,273 US6496594B1 (en) | 1998-10-22 | 1999-10-21 | Method and apparatus for aligning and comparing images of the face and body from different imagers |
US09/422,273 | 1999-10-21 |
Publications (3)
Publication Number | Publication Date |
---|---|
WO2001029769A2 WO2001029769A2 (en) | 2001-04-26 |
WO2001029769A3 WO2001029769A3 (en) | 2002-01-10 |
WO2001029769A9 true WO2001029769A9 (en) | 2002-08-01 |
Family
ID=23674141
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2000/041320 WO2001029769A2 (en) | 1999-10-21 | 2000-10-20 | Method and apparatus for aligning and comparing images of the face and body from different imagers |
Country Status (5)
Country | Link |
---|---|
US (2) | US6496594B1 (en) |
EP (1) | EP1194893A4 (en) |
JP (1) | JP2003512684A (en) |
CA (1) | CA2354594A1 (en) |
WO (1) | WO2001029769A2 (en) |
Families Citing this family (181)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7505941B2 (en) * | 1999-08-31 | 2009-03-17 | American Express Travel Related Services Company, Inc. | Methods and apparatus for conducting electronic transactions using biometrics |
US7953671B2 (en) | 1999-08-31 | 2011-05-31 | American Express Travel Related Services Company, Inc. | Methods and apparatus for conducting electronic transactions |
US7343351B1 (en) | 1999-08-31 | 2008-03-11 | American Express Travel Related Services Company, Inc. | Methods and apparatus for conducting electronic transactions |
US7889052B2 (en) | 2001-07-10 | 2011-02-15 | Xatra Fund Mx, Llc | Authorizing payment subsequent to RF transactions |
JP4396873B2 (en) * | 1999-10-01 | 2010-01-13 | 株式会社資生堂 | How to choose lipstick or eye shadow |
WO2001061523A1 (en) | 2000-02-18 | 2001-08-23 | Cedere Corporation | Automated on-line business bandwidth planning methodology |
US6807290B2 (en) * | 2000-03-09 | 2004-10-19 | Microsoft Corporation | Rapid computer modeling of faces for animation |
JP2001283216A (en) * | 2000-04-03 | 2001-10-12 | Nec Corp | Image collating device, image collating method and recording medium in which its program is recorded |
US6963659B2 (en) * | 2000-09-15 | 2005-11-08 | Facekey Corp. | Fingerprint verification system utilizing a facial image-based heuristic search method |
US6792136B1 (en) * | 2000-11-07 | 2004-09-14 | Trw Inc. | True color infrared photography and video |
JP4310916B2 (en) * | 2000-11-08 | 2009-08-12 | コニカミノルタホールディングス株式会社 | Video display device |
WO2002041188A1 (en) * | 2000-11-15 | 2002-05-23 | Mark Frigon | Method and apparatus for processing objects in online images |
US7020305B2 (en) * | 2000-12-06 | 2006-03-28 | Microsoft Corporation | System and method providing improved head motion estimations for animation |
WO2002061666A1 (en) * | 2001-01-29 | 2002-08-08 | Siemens Aktiengesellschaft | Recognising people using a mobile appliance |
US6654018B1 (en) * | 2001-03-29 | 2003-11-25 | At&T Corp. | Audio-visual selection process for the synthesis of photo-realistic talking-head animations |
US7725427B2 (en) | 2001-05-25 | 2010-05-25 | Fred Bishop | Recurrent billing maintenance with radio frequency payment devices |
US7705732B2 (en) | 2001-07-10 | 2010-04-27 | Fred Bishop | Authenticating an RF transaction using a transaction counter |
US9454752B2 (en) | 2001-07-10 | 2016-09-27 | Chartoleaux Kg Limited Liability Company | Reload protocol at a transaction processing entity |
US7303120B2 (en) | 2001-07-10 | 2007-12-04 | American Express Travel Related Services Company, Inc. | System for biometric security using a FOB |
US8284025B2 (en) | 2001-07-10 | 2012-10-09 | Xatra Fund Mx, Llc | Method and system for auditory recognition biometrics on a FOB |
US20040233038A1 (en) * | 2001-07-10 | 2004-11-25 | American Express Travel Related Services Company, Inc. | Method and system for retinal scan recognition biometrics on a fob |
US9031880B2 (en) | 2001-07-10 | 2015-05-12 | Iii Holdings 1, Llc | Systems and methods for non-traditional payment using biometric data |
US20040239481A1 (en) * | 2001-07-10 | 2004-12-02 | American Express Travel Related Services Company, Inc. | Method and system for facial recognition biometrics on a fob |
US8294552B2 (en) | 2001-07-10 | 2012-10-23 | Xatra Fund Mx, Llc | Facial scan biometrics on a payment device |
US7735725B1 (en) | 2001-07-10 | 2010-06-15 | Fred Bishop | Processing an RF transaction using a routing number |
US7668750B2 (en) | 2001-07-10 | 2010-02-23 | David S Bonalle | Securing RF transactions using a transactions counter |
US9024719B1 (en) | 2001-07-10 | 2015-05-05 | Xatra Fund Mx, Llc | RF transaction system and method for storing user personal data |
US8548927B2 (en) | 2001-07-10 | 2013-10-01 | Xatra Fund Mx, Llc | Biometric registration for facilitating an RF transaction |
US20050116810A1 (en) * | 2001-07-10 | 2005-06-02 | American Express Travel Related Services Company, Inc. | Method and system for vascular pattern recognition biometrics on a fob |
US7360689B2 (en) | 2001-07-10 | 2008-04-22 | American Express Travel Related Services Company, Inc. | Method and system for proffering multiple biometrics for use with a FOB |
US20040236700A1 (en) * | 2001-07-10 | 2004-11-25 | American Express Travel Related Services Company, Inc. | Method and system for keystroke scan recognition biometrics on a fob |
US8001054B1 (en) | 2001-07-10 | 2011-08-16 | American Express Travel Related Services Company, Inc. | System and method for generating an unpredictable number using a seeded algorithm |
US20040236699A1 (en) | 2001-07-10 | 2004-11-25 | American Express Travel Related Services Company, Inc. | Method and system for hand geometry recognition biometrics on a fob |
US7249112B2 (en) | 2002-07-09 | 2007-07-24 | American Express Travel Related Services Company, Inc. | System and method for assigning a funding source for a radio frequency identification device |
US20030063781A1 (en) * | 2001-09-28 | 2003-04-03 | Koninklijke Philips Electronics N.V. | Face recognition from a temporal sequence of face images |
WO2003032005A2 (en) * | 2001-10-09 | 2003-04-17 | Sirf Technologies, Inc. | Method and system for sending location coded images over a wireless network |
JP3849517B2 (en) * | 2001-12-14 | 2006-11-22 | ソニー株式会社 | Photo booth, image processing method, recording medium, and program |
US7221809B2 (en) * | 2001-12-17 | 2007-05-22 | Genex Technologies, Inc. | Face recognition system and method |
JP4023716B2 (en) * | 2001-12-27 | 2007-12-19 | シャープ株式会社 | Resolution correction apparatus, resolution correction program, and computer-readable recording medium recording resolution correction program |
US7286692B2 (en) * | 2001-12-27 | 2007-10-23 | Amnart Kanarat | Automatic celebrity face matching and attractiveness rating machine |
US20040008223A1 (en) * | 2002-03-16 | 2004-01-15 | Catherine Britton | Electronic healthcare management form navigation |
US9848815B2 (en) | 2002-04-22 | 2017-12-26 | Geelux Holdings, Ltd. | Apparatus and method for measuring biologic parameters |
US8328420B2 (en) * | 2003-04-22 | 2012-12-11 | Marcio Marc Abreu | Apparatus and method for measuring biologic parameters |
IL164685A0 (en) | 2002-04-22 | 2005-12-18 | Marcio Marc Aurelio Martins Ab | Apparatus and method for measuring biologic parameters |
SE0201529D0 (en) * | 2002-05-21 | 2002-05-21 | Flir Systems Ab | Method and apparatus for IR camera inspections |
JP2003346149A (en) * | 2002-05-24 | 2003-12-05 | Omron Corp | Face collating device and bioinformation collating device |
EP1516156B1 (en) | 2002-05-30 | 2019-10-23 | AMO Manufacturing USA, LLC | Tracking torsional eye orientation and position |
JP4036051B2 (en) * | 2002-07-30 | 2008-01-23 | オムロン株式会社 | Face matching device and face matching method |
US6805287B2 (en) | 2002-09-12 | 2004-10-19 | American Express Travel Related Services Company, Inc. | System and method for converting a stored value card to a credit card |
US7149358B2 (en) * | 2002-11-27 | 2006-12-12 | General Electric Company | Method and system for improving contrast using multi-resolution contrast based dynamic range management |
US7619626B2 (en) * | 2003-03-01 | 2009-11-17 | The Boeing Company | Mapping images from one or more sources into an image for display |
US7711155B1 (en) * | 2003-04-14 | 2010-05-04 | Videomining Corporation | Method and system for enhancing three dimensional face modeling using demographic classification |
US7242807B2 (en) * | 2003-05-05 | 2007-07-10 | Fish & Richardson P.C. | Imaging of biometric information based on three-dimensional shapes |
US7421097B2 (en) * | 2003-05-27 | 2008-09-02 | Honeywell International Inc. | Face identification verification using 3 dimensional modeling |
JP4366119B2 (en) * | 2003-05-29 | 2009-11-18 | キヤノン株式会社 | Document processing device |
US7458683B2 (en) * | 2003-06-16 | 2008-12-02 | Amo Manufacturing Usa, Llc | Methods and devices for registering optical measurement datasets of an optical system |
US7317816B2 (en) * | 2003-08-19 | 2008-01-08 | Intel Corporation | Enabling content-based search of objects in an image database with reduced matching |
WO2005020030A2 (en) * | 2003-08-22 | 2005-03-03 | University Of Houston | Multi-modal face recognition |
US20050111705A1 (en) * | 2003-08-26 | 2005-05-26 | Roman Waupotitsch | Passive stereo sensing for 3D facial shape biometrics |
US7990384B2 (en) * | 2003-09-15 | 2011-08-02 | At&T Intellectual Property Ii, L.P. | Audio-visual selection process for the synthesis of photo-realistic talking-head animations |
JP4615272B2 (en) * | 2003-09-29 | 2011-01-19 | 富士フイルム株式会社 | Authentication system, program, and building |
US20050123182A1 (en) * | 2003-12-03 | 2005-06-09 | Avision Inc. | Temperature sensor |
US10227063B2 (en) | 2004-02-26 | 2019-03-12 | Geelux Holdings, Ltd. | Method and apparatus for biological evaluation |
WO2006078265A2 (en) * | 2004-03-30 | 2006-07-27 | Geometrix | Efficient classification of three dimensional face models for human identification and other applications |
JP4059224B2 (en) * | 2004-04-13 | 2008-03-12 | 株式会社デンソー | Driver appearance recognition system |
US7318550B2 (en) | 2004-07-01 | 2008-01-15 | American Express Travel Related Services Company, Inc. | Biometric safeguard method for use with a smartcard |
US20060016873A1 (en) * | 2004-07-01 | 2006-01-26 | American Express Travel Related Services Company, Inc. | Method and system for retinal scan recognition biometrics on a smartcard |
US7341181B2 (en) | 2004-07-01 | 2008-03-11 | American Express Travel Related Services Company, Inc. | Method for biometric security using a smartcard |
US7325724B2 (en) | 2004-07-01 | 2008-02-05 | American Express Travel Related Services Company, Inc. | Method for registering a biometric for use with a smartcard |
US7314165B2 (en) | 2004-07-01 | 2008-01-01 | American Express Travel Related Services Company, Inc. | Method and system for smellprint recognition biometrics on a smartcard |
US20060000895A1 (en) * | 2004-07-01 | 2006-01-05 | American Express Travel Related Services Company, Inc. | Method and system for facial recognition biometrics on a smartcard |
US20060016872A1 (en) * | 2004-07-01 | 2006-01-26 | American Express Travel Related Services Company, Inc. | Method and system for iris scan recognition biometrics on a smartcard |
WO2006006559A1 (en) * | 2004-07-09 | 2006-01-19 | Intellectual Property Bank Corp. | Method for acquiring bioinformation using millimeter-wave band electromagnetic wave, device for acquiring and displaying bioinformation |
WO2006006081A2 (en) * | 2004-07-09 | 2006-01-19 | Emitall Surveillance S.A. | Smart video surveillance system ensuring privacy |
JP4340618B2 (en) * | 2004-10-08 | 2009-10-07 | 富士通株式会社 | Biometric information authentication apparatus and method, biometric information authentication program, and computer-readable recording medium recording the biometric information authentication program |
WO2006051488A1 (en) * | 2004-11-10 | 2006-05-18 | Koninklijke Philips Electronics N.V. | System and method for registration of medical images |
US7469060B2 (en) * | 2004-11-12 | 2008-12-23 | Honeywell International Inc. | Infrared face detection and recognition system |
US7469074B2 (en) * | 2004-11-17 | 2008-12-23 | Lexmark International, Inc. | Method for producing a composite image by processing source images to align reference points |
US8049594B1 (en) | 2004-11-30 | 2011-11-01 | Xatra Fund Mx, Llc | Enhanced RFID instrument security |
EP1831849A1 (en) * | 2004-12-27 | 2007-09-12 | Emitall Surveillance S.A. | Efficient scrambling of regions of interest in an image or video to preserve privacy |
US20060140444A1 (en) * | 2004-12-27 | 2006-06-29 | Yih-Ran Sheu | Human face identification means in security system |
US7548776B2 (en) * | 2005-02-08 | 2009-06-16 | Southern Taiwan University Of Technology | Method and system for performing fever triage |
US7925391B2 (en) * | 2005-06-02 | 2011-04-12 | The Boeing Company | Systems and methods for remote display of an enhanced image |
GB0512869D0 (en) * | 2005-06-24 | 2005-08-03 | Ibm | Method and system for facial recognition in groups |
US20070038059A1 (en) * | 2005-07-07 | 2007-02-15 | Garrett Sheffer | Implant and instrument morphing |
JP4624882B2 (en) * | 2005-08-01 | 2011-02-02 | 株式会社東海理化電機製作所 | Personal authentication device and personal authentication method |
JP4750520B2 (en) * | 2005-09-21 | 2011-08-17 | 富士フイルム株式会社 | Human image correction apparatus and method |
EP1951110B1 (en) | 2005-10-24 | 2012-10-03 | Marcio Marc Aurelio Martins Abreu | Apparatus for measuring biologic parameters |
US8064716B2 (en) * | 2005-11-08 | 2011-11-22 | Soundstarts, Inc. | Apparatus and methods for enhancing digital images |
US7953253B2 (en) * | 2005-12-31 | 2011-05-31 | Arcsoft, Inc. | Face detection on mobile devices |
US7643659B2 (en) * | 2005-12-31 | 2010-01-05 | Arcsoft, Inc. | Facial feature detection on mobile devices |
US7822259B2 (en) * | 2006-05-26 | 2010-10-26 | Areva Np Inc. | Method for positive identification of inner surface and outer surface of sample flakes |
EP2054838A4 (en) * | 2006-08-15 | 2012-08-15 | Univ Texas | Methods, compositions and systems for analyzing imaging data |
US7921120B2 (en) * | 2006-11-30 | 2011-04-05 | D&S Consultants | Method and system for image recognition using a similarity inverse matrix |
US8380558B1 (en) * | 2006-12-21 | 2013-02-19 | Videomining Corporation | Method and system for analyzing shopping behavior in a store by associating RFID data with video-based behavior and segmentation data |
US8665333B1 (en) * | 2007-01-30 | 2014-03-04 | Videomining Corporation | Method and system for optimizing the observation and annotation of complex human behavior from video sources |
JP5061645B2 (en) * | 2007-02-26 | 2012-10-31 | ソニー株式会社 | Information extraction method, information extraction device, program, registration device, and verification device |
GB2448050A (en) * | 2007-03-22 | 2008-10-01 | Artnix Inc | A method and apparatus for extracting face images from video data and performing recognition matching for identification of people. |
US8918162B2 (en) * | 2007-04-17 | 2014-12-23 | Francine J. Prokoski | System and method for using three dimensional infrared imaging to provide psychological profiles of individuals |
US7848548B1 (en) * | 2007-06-11 | 2010-12-07 | Videomining Corporation | Method and system for robust demographic classification using pose independent model from sequence of face images |
US7857452B2 (en) * | 2007-08-27 | 2010-12-28 | Catholic Healthcare West | Eye movements as a way to determine foci of covert attention |
JP4466702B2 (en) * | 2007-09-12 | 2010-05-26 | カシオ計算機株式会社 | Imaging apparatus and imaging control program |
US7996762B2 (en) * | 2007-09-21 | 2011-08-09 | Microsoft Corporation | Correlative multi-label image annotation |
US8994747B2 (en) * | 2007-11-09 | 2015-03-31 | Imacor Inc. | Superimposed display of image contours |
US8540158B2 (en) * | 2007-12-12 | 2013-09-24 | Yiwu Lei | Document verification using dynamic document identification framework |
US8194933B2 (en) * | 2007-12-12 | 2012-06-05 | 3M Innovative Properties Company | Identification and verification of an unknown document according to an eigen image process |
DE102009014437B4 (en) | 2008-03-26 | 2023-01-19 | Continental Autonomous Mobility Germany GmbH | Object Recognition System and Method |
WO2009124139A1 (en) * | 2008-04-01 | 2009-10-08 | The Government Of The United States Of America, As Represented By The Secretaty Of The Navy | Methods and systems of comparing face models for recognition |
US20090319601A1 (en) * | 2008-06-22 | 2009-12-24 | Frayne Raymond Zvonaric | Systems and methods for providing real-time video comparison |
US8204340B2 (en) * | 2008-09-29 | 2012-06-19 | Two Pic Mc Llc | Methods and apparatus for dot marker matching |
US9144397B2 (en) * | 2008-12-04 | 2015-09-29 | Real Imaging Ltd. | Method apparatus and system for determining a thermal signature |
EP2411963B1 (en) * | 2009-03-27 | 2019-05-08 | Koninklijke Philips N.V. | Improvements to medical imaging |
WO2011049558A1 (en) * | 2009-10-20 | 2011-04-28 | Catholic Healthcare West | Eye movements as a way to determine foci of covert attention |
US8634900B2 (en) | 2009-11-11 | 2014-01-21 | Koninklijke Philips N.V. | Mask comfort diagnostic method |
US8509482B2 (en) * | 2009-12-21 | 2013-08-13 | Canon Kabushiki Kaisha | Subject tracking apparatus, subject region extraction apparatus, and control methods therefor |
US9900524B2 (en) | 2009-12-24 | 2018-02-20 | Flir Systems, Inc. | Cameras with on-board reporting capabilities |
US20110182493A1 (en) * | 2010-01-25 | 2011-07-28 | Martin Huber | Method and a system for image annotation |
EP2545531B1 (en) * | 2010-03-10 | 2018-06-13 | ELC Management LLC | System for skin treatment analysis using spectral image data to generate 3d rgb model |
WO2011152842A1 (en) * | 2010-06-01 | 2011-12-08 | Hewlett-Packard Development Company, L.P. | Face morphing based on learning |
US8311337B2 (en) | 2010-06-15 | 2012-11-13 | Cyberlink Corp. | Systems and methods for organizing and accessing feature vectors in digital images |
US8638364B2 (en) | 2010-09-23 | 2014-01-28 | Sony Computer Entertainment Inc. | User interface system and method using thermal imaging |
US8786698B2 (en) | 2010-09-23 | 2014-07-22 | Sony Computer Entertainment Inc. | Blow tracking user interface system and method |
US11309081B2 (en) | 2010-10-13 | 2022-04-19 | Gholam A. Peyman | Telemedicine system with dynamic imaging |
US10456209B2 (en) * | 2010-10-13 | 2019-10-29 | Gholam A. Peyman | Remote laser treatment system with dynamic imaging |
JP5648452B2 (en) * | 2010-12-03 | 2015-01-07 | 富士通株式会社 | Image processing program and image processing apparatus |
US20120243751A1 (en) * | 2011-03-24 | 2012-09-27 | Zhihong Zheng | Baseline face analysis |
US9143703B2 (en) * | 2011-06-10 | 2015-09-22 | Flir Systems, Inc. | Infrared camera calibration techniques |
FR2979728B1 (en) * | 2011-09-01 | 2016-05-13 | Morpho | FRAUD DETECTION FOR BIOMETRIC TYPE ACCESS CONTROL SYSTEM |
US20130148811A1 (en) * | 2011-12-08 | 2013-06-13 | Sony Ericsson Mobile Communications Ab | Electronic Devices, Methods, and Computer Program Products for Determining Position Deviations in an Electronic Device and Generating a Binaural Audio Signal Based on the Position Deviations |
US9088697B2 (en) | 2011-12-13 | 2015-07-21 | Google Inc. | Processing media streams during a multi-user video conference |
US9088426B2 (en) * | 2011-12-13 | 2015-07-21 | Google Inc. | Processing media streams during a multi-user video conference |
US8655152B2 (en) | 2012-01-31 | 2014-02-18 | Golden Monkey Entertainment | Method and system of presenting foreign films in a native language |
US9020192B2 (en) * | 2012-04-11 | 2015-04-28 | Access Business Group International Llc | Human submental profile measurement |
US10452894B2 (en) * | 2012-06-26 | 2019-10-22 | Qualcomm Incorporated | Systems and method for facial verification |
US9224248B2 (en) * | 2012-07-12 | 2015-12-29 | Ulsee Inc. | Method of virtual makeup achieved by facial tracking |
KR101415848B1 (en) | 2012-12-12 | 2014-07-09 | 휴앤에스(주) | Monitering apparatus of school-zone using detection of human body and vehicle |
US9390149B2 (en) * | 2013-01-16 | 2016-07-12 | International Business Machines Corporation | Converting text content to a set of graphical icons |
US8924735B2 (en) * | 2013-02-15 | 2014-12-30 | Microsoft Corporation | Managed biometric identity |
SG11201507344WA (en) | 2013-03-12 | 2015-10-29 | Steven P Lee | Computerized refraction and astigmatism determination |
US9274052B2 (en) * | 2013-07-10 | 2016-03-01 | Canon Kabushiki Kaisha | Feature vector for classifying specular objects based on material type |
US9367909B2 (en) | 2013-07-10 | 2016-06-14 | Canon Kabushiki Kaisha | Devices, systems, and methods for classifying materials based on a bidirectional reflectance distribution function |
US9996726B2 (en) | 2013-08-02 | 2018-06-12 | Qualcomm Incorporated | Feature identification using an RGB-NIR camera pair |
CA2980062A1 (en) | 2013-10-11 | 2015-04-16 | Marcio Marc Abreu | Method and apparatus for biological evaluation |
US9347899B2 (en) | 2013-12-06 | 2016-05-24 | Rolls-Royce Corporation | Thermographic inspection techniques |
JP2017501844A (en) | 2014-01-10 | 2017-01-19 | マーシオ マーク アブリュー | Device for measuring the infrared output of an Abreu brain thermal tunnel |
CA2936235A1 (en) | 2014-01-10 | 2015-07-16 | Marcio Marc Abreu | Devices to monitor and provide treatment at an abreu brain tunnel |
AU2015209304A1 (en) | 2014-01-22 | 2016-07-21 | Marcio Marc Abreu | Devices configured to provide treatment at an Abreu brain thermal tunnel |
CN110717446B (en) | 2014-03-13 | 2023-11-07 | 日本电气株式会社 | Detection apparatus, detection method, and recording medium |
KR101601475B1 (en) * | 2014-08-25 | 2016-03-21 | 현대자동차주식회사 | Pedestrian detection device and method for driving vehicle at night |
JP6426433B2 (en) * | 2014-10-27 | 2018-11-21 | 株式会社日立製作所 | Image processing apparatus, image processing method, POI information creation system, warning system, and guidance system |
WO2016083483A1 (en) * | 2014-11-27 | 2016-06-02 | Koninklijke Philips N.V. | Imaging device and method for generating an image of a patient |
US10037528B2 (en) | 2015-01-14 | 2018-07-31 | Tactilis Sdn Bhd | Biometric device utilizing finger sequence for authentication |
US9607189B2 (en) | 2015-01-14 | 2017-03-28 | Tactilis Sdn Bhd | Smart card system comprising a card and a carrier |
US10395227B2 (en) | 2015-01-14 | 2019-08-27 | Tactilis Pte. Limited | System and method for reconciling electronic transaction records for enhanced security |
WO2016145215A1 (en) | 2015-03-10 | 2016-09-15 | Marcio Marc Abreu | Devices, apparatuses, systems, and methods for measuring temperature of an abtt terminus |
EP3274986A4 (en) | 2015-03-21 | 2019-04-17 | Mine One GmbH | Virtual 3d methods, systems and software |
US10853625B2 (en) | 2015-03-21 | 2020-12-01 | Mine One Gmbh | Facial signature methods, systems and software |
US9430697B1 (en) * | 2015-07-03 | 2016-08-30 | TCL Research America Inc. | Method and system for face recognition using deep collaborative representation-based classification |
JP6564271B2 (en) * | 2015-08-07 | 2019-08-21 | キヤノン株式会社 | Imaging apparatus, image processing method, program, and storage medium |
US10614288B2 (en) * | 2015-12-31 | 2020-04-07 | Cerner Innovation, Inc. | Methods and systems for detecting stroke symptoms |
JP6829001B2 (en) * | 2016-03-18 | 2021-02-10 | 医療法人社団皓有会 | Blood pressure information estimation device |
US10210320B2 (en) * | 2016-09-21 | 2019-02-19 | Lextron Systems, Inc. | System and method for secure 5-D user identification |
US10398316B1 (en) * | 2016-09-30 | 2019-09-03 | Vium, Inc. | Method and apparatus for determining physiological characteristics of experimental animals based upon infrared and visible light images |
JP6809262B2 (en) * | 2017-02-08 | 2021-01-06 | トヨタ自動車株式会社 | Driver status detector |
US10275425B2 (en) * | 2017-02-14 | 2019-04-30 | Henry Edward Kernan | Method for compressing, slicing, and transmitting image files for display and interpretation |
US10412286B2 (en) | 2017-03-31 | 2019-09-10 | Westboro Photonics Inc. | Multicamera imaging system and method for measuring illumination |
CN108875474A (en) * | 2017-07-18 | 2018-11-23 | 北京旷视科技有限公司 | Assess the method, apparatus and computer storage medium of face recognition algorithms |
US10289899B2 (en) * | 2017-08-31 | 2019-05-14 | Banuba Limited | Computer-implemented methods and computer systems for real-time detection of human's emotions from visual recordings |
CN115937776A (en) * | 2017-09-15 | 2023-04-07 | 杭州海康威视数字技术股份有限公司 | Monitoring method, device, system, electronic equipment and computer readable storage medium |
TWI625679B (en) * | 2017-10-16 | 2018-06-01 | 緯創資通股份有限公司 | Live facial recognition method and system |
US10643446B2 (en) | 2017-12-28 | 2020-05-05 | Cerner Innovation, Inc. | Utilizing artificial intelligence to detect objects or patient safety events in a patient room |
CN112580423A (en) * | 2019-09-30 | 2021-03-30 | 托比股份公司 | Method of processing an image of a user's eyes, associated system and computer program |
IT201900018230A1 (en) * | 2019-10-08 | 2021-04-08 | Zoeen S R L | DISPLAY DEVICE FOR SUB-SURFACE STRUCTURES AND METHOD OF VISUALIZATION OF SUCH SUB-SURFACE STRUCTURES |
KR102203786B1 (en) * | 2019-11-14 | 2021-01-15 | 오로라월드 주식회사 | Method and System for Providing Interaction Service Using Smart Toy |
JP2020074241A (en) * | 2020-02-12 | 2020-05-14 | 日本電気株式会社 | Detector |
US11307098B2 (en) | 2020-03-27 | 2022-04-19 | Ecb Consulting Llc | Systems and approaches for obtaining temperature measurements using thermal imaging |
US11326956B2 (en) * | 2020-08-06 | 2022-05-10 | Motorola Solutions, Inc. | Face and inner canthi detection for thermographic body temperature measurement |
US11204281B1 (en) * | 2020-09-03 | 2021-12-21 | Sensormatic Electronics, LLC | Enhanced temperature measurement techniques |
RU203731U1 (en) * | 2020-12-21 | 2021-04-19 | федеральное государственное бюджетное образовательное учреждение высшего образования "Кемеровский государственный университет" (КемГУ) | SOFTWARE DEVICE FOR AUTOMATED CONTACTLESS DETECTION OF INCREASED TEMPERATURE ON THE BODY SURFACE AND BIOMETRIC IDENTIFICATION |
CN117058131B (en) * | 2023-10-11 | 2024-03-19 | 深圳市鹰瞳智能技术有限公司 | Method for carrying out visual positioning on facial artery based on high-resolution thermal imaging |
CN117084654B (en) * | 2023-10-19 | 2024-01-12 | 深圳市鹰瞳智能技术有限公司 | Method and system for evaluating ocular artery collateral blood flow dynamics based on facial thermal image |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4975969A (en) * | 1987-10-22 | 1990-12-04 | Peter Tal | Method and apparatus for uniquely identifying individuals by particular physical characteristics and security system utilizing the same |
US5163094A (en) | 1991-03-20 | 1992-11-10 | Francine J. Prokoski | Method for identifying individuals from analysis of elemental shapes derived from biosensor data |
US5659626A (en) * | 1994-10-20 | 1997-08-19 | Calspan Corporation | Fingerprint identification system |
US5687259A (en) * | 1995-03-17 | 1997-11-11 | Virtual Eyes, Incorporated | Aesthetic imaging system |
US5809171A (en) * | 1996-01-05 | 1998-09-15 | Mcdonnell Douglas Corporation | Image processing method and apparatus for correlating a test image with a template |
US6173068B1 (en) * | 1996-07-29 | 2001-01-09 | Mikos, Ltd. | Method and apparatus for recognizing and classifying individuals based on minutiae |
US5775806A (en) * | 1996-09-12 | 1998-07-07 | The United States Of America As Represented By The Secretary Of The Air Force | Infrared assessment system |
US5991429A (en) * | 1996-12-06 | 1999-11-23 | Coffin; Jeffrey S. | Facial recognition system for security access and identification |
US6111978A (en) * | 1996-12-13 | 2000-08-29 | International Business Machines Corporation | System and method for determining ridge counts in fingerprint image processing |
US6072895A (en) * | 1996-12-13 | 2000-06-06 | International Business Machines Corporation | System and method using minutiae pruning for fingerprint image processing |
KR19990016896A (en) * | 1997-08-20 | 1999-03-15 | 전주범 | Eye region detection method in face image |
US6142876A (en) * | 1997-08-22 | 2000-11-07 | Cumbers; Blake | Player tracking and identification system |
US6049621A (en) * | 1997-08-22 | 2000-04-11 | International Business Machines Corporation | Determining a point correspondence between two points in two respective (fingerprint) images |
US6002782A (en) * | 1997-11-12 | 1999-12-14 | Unisys Corporation | System and method for recognizing a 3-D object by generating a 2-D image of the object from a transformed 3-D model |
US6134340A (en) * | 1997-12-22 | 2000-10-17 | Trw Inc. | Fingerprint feature correlator |
-
1999
- 1999-10-21 US US09/422,273 patent/US6496594B1/en not_active Expired - Lifetime
-
2000
- 2000-10-20 JP JP2001532489A patent/JP2003512684A/en active Pending
- 2000-10-20 CA CA002354594A patent/CA2354594A1/en not_active Abandoned
- 2000-10-20 WO PCT/US2000/041320 patent/WO2001029769A2/en not_active Application Discontinuation
- 2000-10-20 EP EP00986798A patent/EP1194893A4/en not_active Withdrawn
-
2002
- 2002-07-15 US US10/195,629 patent/US6751340B2/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
EP1194893A4 (en) | 2004-05-26 |
WO2001029769A3 (en) | 2002-01-10 |
US6496594B1 (en) | 2002-12-17 |
US20030108223A1 (en) | 2003-06-12 |
WO2001029769A2 (en) | 2001-04-26 |
CA2354594A1 (en) | 2001-04-26 |
US6751340B2 (en) | 2004-06-15 |
EP1194893A2 (en) | 2002-04-10 |
JP2003512684A (en) | 2003-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6751340B2 (en) | Method and apparatus for aligning and comparing images of the face and body from different imagers | |
AU2007284299B2 (en) | A system for iris detection, tracking and recognition at a distance | |
Prokoski | History, current status, and future of infrared identification | |
Burge et al. | Ear biometrics | |
CA2083380C (en) | Method for identifying individuals from analysis of elemental shapes derived from biosensor data | |
Nowara et al. | Ppgsecure: Biometric presentation attack detection using photopletysmograms | |
Burge et al. | Ear biometrics in computer vision | |
US6173068B1 (en) | Method and apparatus for recognizing and classifying individuals based on minutiae | |
US6920236B2 (en) | Dual band biometric identification system | |
CN109558764A (en) | Face identification method and device, computer equipment | |
Prokoski et al. | Infrared identification of faces and body parts | |
Nurhudatiana et al. | On criminal identification in color skin images using skin marks (RPPVSM) and fusion with inferred vein patterns | |
Sathish et al. | Multi-algorithmic iris recognition | |
Medioni et al. | Non-cooperative persons identification at a distance with 3D face modeling | |
Kanade | Identification of Human Faces | |
Yoshino | Recent advances in facial image identification | |
Heenaye et al. | A study of dorsal vein pattern for biometric security | |
Ibitayo et al. | Development Of Iris Based Age And Gender Detection System | |
Prokoski et al. | 9 INFRARED IDENTIFICATION OF | |
Burge et al. | 13EAR BIOMETRICS | |
Wang | Investigation of infrared hand vein pattern biometrics | |
Tansuriyavong et al. | Person Identification by Multi-Directional Face Recognition while Walking in a Room | |
Vatsa et al. | Video Biometrics | |
Srivani et al. | A SURVEY ON THE FACE IDENTIFICATION METHODS |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): CA JP |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
ENP | Entry into the national phase |
Ref document number: 2354594 Country of ref document: CA Ref country code: CA Ref document number: 2354594 Kind code of ref document: A Format of ref document f/p: F |
|
ENP | Entry into the national phase |
Ref country code: JP Ref document number: 2001 532489 Kind code of ref document: A Format of ref document f/p: F |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2000986798 Country of ref document: EP |
|
AK | Designated states |
Kind code of ref document: A3 Designated state(s): CA JP |
|
AL | Designated countries for regional patents |
Kind code of ref document: A3 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
WWP | Wipo information: published in national office |
Ref document number: 2000986798 Country of ref document: EP |
|
AK | Designated states |
Kind code of ref document: C2 Designated state(s): CA JP |
|
AL | Designated countries for regional patents |
Kind code of ref document: C2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
COP | Corrected version of pamphlet |
Free format text: PAGES 1/14-14/14, DRAWINGS, REPLACED BY NEW PAGES 1/12-12/12 |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: 2000986798 Country of ref document: EP |