CN104392216A - Three-dimensional face recognition method for door lock - Google Patents
Three-dimensional face recognition method for door lock Download PDFInfo
- Publication number
- CN104392216A CN104392216A CN201410668841.XA CN201410668841A CN104392216A CN 104392216 A CN104392216 A CN 104392216A CN 201410668841 A CN201410668841 A CN 201410668841A CN 104392216 A CN104392216 A CN 104392216A
- Authority
- CN
- China
- Prior art keywords
- face
- curve
- point
- dimensional face
- diametral
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- 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
- G06V40/172—Classification, e.g. identification
Abstract
The invention discloses a three-dimensional face recognition method for a door lock. The method comprises the following steps: (1) preprocessing a three-dimensional face; (2) extracting a plurality of radial curves radiated from the apex nasi point of the three-dimensional face, sampling the radial curves again, extracting usable points, and then building a point correspondence relation of the curves for reducing the influence of the data loss and shielding of hair on the face recognition effect; (3) performing layered elastic matching for each radial curve of the three-dimensional face and the corresponding curve of the face stored in a library; (4) matching the curves based on the distance from the corresponding point to the apex nasi point according to the built point correspondence relation of the tested face and the face stored in the library; (5) performing weight fusion for the two matching similarity of each curve to obtain the total similarity for recognizing. The method shows a good effect on matching the deformation graphics; the influence caused by the change on expression can be effectively overcome; therefore, the influence of the data loss and shielding of the air on the face recognition effect can be effectively reduced.
Description
Technical field
The invention belongs to face identification method, be specifically related to a kind of three-dimensional face identification method for door lock.
Background technology
Recognition of face has the feature such as noncontact, good concealment and becomes the study hotspot of present mode identification and computer vision field.Traditional two-dimension human face identification based on two dimensional gray or coloured image has obtained good recognition performance, but still is subject to the impact of the factors such as illumination attitude, expression, and its essential reason is that image is the brief projection of three-dimensional body at two-dimensional space.
The research of current regarding three-dimensional face identification method has a lot, can be divided into directly mating based on spatial domain, based on global feature coupling and the three-dimensional face identification method based on local feature coupling according to characteristic formp.Existing recognition methods discrimination is not high, and to expression, to block and noise has poor robustness.
Summary of the invention
For the deficiency that prior art exists, the object of the invention is to provide a kind of three-dimensional face identification method for door lock, has good recognition performance, and to expression, to block and noise has good robustness.
To achieve these goals, the present invention realizes by the following technical solutions:
A kind of three-dimensional face identification method for door lock of the present invention, comprises following step:
(1) pre-service is carried out to three-dimensional face;
(2) extract on three-dimensional face from many facial diametral curves that prenasale is launched, and extract useful point after resampling is carried out to diametral curve, and the point correspondence set up between curve, block impact on recognition of face effect for reducing loss of data and hair;
(3) layering Elastic Matching is carried out to test every bar three-dimensional face diametral curve of face and the homologous thread of storehouse collection face;
(4) again according to the point correspondence that test face and storehouse collection face are set up, corresponding point are utilized to arrive the distance match curve of prenasale;
(5) two kinds of matching similarities of every bar curve are weighted fusion to be used for identifying as total similarity.
In step (1), the pretreated method of three-dimensional face is as follows:
(1a) prenasale and cutting zone is determined;
(2a) three-dimensional face point cloud smoothing denoising;
(3a) human face posture corrects.
In step (2), the method that face diametral curve extracts is as follows:
On calculating face point cloud, each point is to the distance of this plane, and chosen distance is less than the set of the point of threshold value as diametral curve; Then plane is pivoted, and hand over three-dimensional face curved surface S-phase and obtain diametral curve.
In step (2), the method for diametral curve being carried out to resampling is as follows:
To any point on a sample reference curve, whether this position of service marking comprises sampled point; If reference curve exists sampled point on the correspondence position of 1mm during resampling, then the mark of this position of reference curve is set to 1, otherwise is set to 0.
In step (3), the layering Elastic Matching method of three-dimensional face diametral curve is as follows:
(1b) shape tree of the every bar curve of storehouse collection face is set up;
(2b) corresponding with on test set face curve for layered Elastic Matching;
(3b) fusion is weighted to all similarities and obtains layering and matching similarity.
Method curve layering Elastic Matching algorithm of the present invention make use of the whole and part geological information of curve well, has good effect to the coupling of deformation figure; Give different weights to every bar diametral curve according to the order of severity of its expression influence, effectively can overcome the impact that expression shape change is brought; By setting up the corresponding relation between curve sampled point, diametral curve being carried out to the extraction of useful point, effectively reducing loss of data and hair and blocking impact on recognition of face effect.
Embodiment
The technological means realized for making the present invention, creation characteristic, reaching object and effect is easy to understand, below in conjunction with embodiment, setting forth the present invention further.
A kind of three-dimensional face identification method for door lock of the present invention, comprises following step:
(1) pre-service is carried out to three-dimensional face;
(2) extract on three-dimensional face from many facial diametral curves that prenasale is launched, and extract useful point after resampling is carried out to diametral curve, and the point correspondence set up between curve, block impact on recognition of face effect for reducing loss of data and hair;
(3) layering Elastic Matching is carried out to test every bar three-dimensional face diametral curve of face and the homologous thread of storehouse collection face;
(4) again according to the point correspondence that test face and storehouse collection face are set up, corresponding point are utilized to arrive the distance match curve of prenasale;
(5) two kinds of matching similarities of every bar curve are weighted fusion to be used for identifying as total similarity.
In the present embodiment, in step (1), the pretreated method of three-dimensional face is as follows:
(1a) prenasale and cutting zone is determined;
(2a) three-dimensional face point cloud smoothing denoising;
(3a) human face posture corrects.
In the present embodiment, in step (2), the method that face diametral curve extracts is as follows:
On calculating face point cloud, each point is to the distance of this plane, and chosen distance is less than the set of the point of threshold value as diametral curve; Then plane is pivoted, and hand over three-dimensional face curved surface S-phase and obtain diametral curve.
In the present embodiment, in step (2), the method for diametral curve being carried out to resampling is as follows:
To any point on a sample reference curve, whether this position of service marking comprises sampled point; If reference curve exists sampled point on the correspondence position of 1mm during resampling, then the mark of this position of reference curve is set to 1, otherwise is set to 0.
In the present embodiment, in step (3), the layering Elastic Matching method of three-dimensional face diametral curve is as follows:
(1b) shape tree of the every bar curve of storehouse collection face is set up;
(2b) corresponding with on test set face curve for layered Elastic Matching;
(3b) fusion is weighted to all similarities and obtains layering and matching similarity.
Method curve layering Elastic Matching algorithm of the present invention make use of the whole and part geological information of curve well, has good effect to the coupling of deformation figure; Give different weights to every bar diametral curve according to the order of severity of its expression influence, effectively can overcome the impact that expression shape change is brought; By setting up the corresponding relation between curve sampled point, diametral curve being carried out to the extraction of useful point, effectively reducing loss of data and hair and blocking impact on recognition of face effect.
More than show and describe ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; what describe in above-described embodiment and instructions just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.Application claims protection domain is defined by appending claims and equivalent thereof.
Claims (5)
1. for a three-dimensional face identification method for door lock, it is characterized in that, comprise following step:
(1) pre-service is carried out to three-dimensional face;
(2) extract on three-dimensional face from many facial diametral curves that prenasale is launched, and extract useful point after resampling is carried out to diametral curve, and the point correspondence set up between curve, block impact on recognition of face effect for reducing loss of data and hair;
(3) layering Elastic Matching is carried out to test every bar three-dimensional face diametral curve of face and the homologous thread of storehouse collection face;
(4) again according to the point correspondence that test face and storehouse collection face are set up, corresponding point are utilized to arrive the distance match curve of prenasale;
(5) two kinds of matching similarities of every bar curve are weighted fusion to be used for identifying as total similarity.
2. the three-dimensional face identification method for door lock according to claim 1, is characterized in that, in step (1), the pretreated method of three-dimensional face is as follows:
(1a) prenasale and cutting zone is determined;
(2a) three-dimensional face point cloud smoothing denoising;
(3a) human face posture corrects.
3. the three-dimensional face identification method for door lock according to claim 1, is characterized in that, in step (2), the method that face diametral curve extracts is as follows:
On calculating face point cloud, each point is to the distance of this plane, and chosen distance is less than the set of the point of threshold value as diametral curve; Then plane is pivoted, and hand over three-dimensional face curved surface S-phase and obtain diametral curve.
4. the three-dimensional face identification method for door lock according to claim 1, is characterized in that, in step (2), the method for diametral curve being carried out to resampling is as follows:
To any point on a sample reference curve, whether this position of service marking comprises sampled point; If reference curve exists sampled point on the correspondence position of 1mm during resampling, then the mark of this position of reference curve is set to 1, otherwise is set to 0.
5. the three-dimensional face identification method for door lock according to claim 1, is characterized in that, in step (3), the layering Elastic Matching method of three-dimensional face diametral curve is as follows:
(1b) shape tree of the every bar curve of storehouse collection face is set up;
(2b) corresponding with on test set face curve for layered Elastic Matching;
(3b) fusion is weighted to all similarities and obtains layering and matching similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410668841.XA CN104392216A (en) | 2014-11-20 | 2014-11-20 | Three-dimensional face recognition method for door lock |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410668841.XA CN104392216A (en) | 2014-11-20 | 2014-11-20 | Three-dimensional face recognition method for door lock |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104392216A true CN104392216A (en) | 2015-03-04 |
Family
ID=52610117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410668841.XA Pending CN104392216A (en) | 2014-11-20 | 2014-11-20 | Three-dimensional face recognition method for door lock |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104392216A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109960975A (en) * | 2017-12-23 | 2019-07-02 | 四川大学 | A kind of face generation and its face identification method based on human eye |
| CN110570549A (en) * | 2019-07-26 | 2019-12-13 | 华中科技大学 | Intelligent unlocking method and corresponding device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6775397B1 (en) * | 2000-02-24 | 2004-08-10 | Nokia Corporation | Method and apparatus for user recognition using CCD cameras |
| US20040240711A1 (en) * | 2003-05-27 | 2004-12-02 | Honeywell International Inc. | Face identification verification using 3 dimensional modeling |
| CN103268654A (en) * | 2013-05-30 | 2013-08-28 | 苏州福丰科技有限公司 | Electronic lock based on three-dimensional face identification |
| CN103268653A (en) * | 2013-05-30 | 2013-08-28 | 苏州福丰科技有限公司 | Face identification method for access control system |
-
2014
- 2014-11-20 CN CN201410668841.XA patent/CN104392216A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6775397B1 (en) * | 2000-02-24 | 2004-08-10 | Nokia Corporation | Method and apparatus for user recognition using CCD cameras |
| US20040240711A1 (en) * | 2003-05-27 | 2004-12-02 | Honeywell International Inc. | Face identification verification using 3 dimensional modeling |
| CN103268654A (en) * | 2013-05-30 | 2013-08-28 | 苏州福丰科技有限公司 | Electronic lock based on three-dimensional face identification |
| CN103268653A (en) * | 2013-05-30 | 2013-08-28 | 苏州福丰科技有限公司 | Face identification method for access control system |
Non-Patent Citations (1)
| Title |
|---|
| 潘仁林等: ""基于面部曲线弹性匹配的三维人脸识别方法"", 《图学学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109960975A (en) * | 2017-12-23 | 2019-07-02 | 四川大学 | A kind of face generation and its face identification method based on human eye |
| CN109960975B (en) * | 2017-12-23 | 2022-07-01 | 四川大学 | Human face generation and human face recognition method based on human eyes |
| CN110570549A (en) * | 2019-07-26 | 2019-12-13 | 华中科技大学 | Intelligent unlocking method and corresponding device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657631B (en) | Human body posture recognition method and device | |
| CN102880877B (en) | Target identification method based on contour features | |
| CN102779269B (en) | Human face identification algorithm based on image sensor imaging system | |
| Kim et al. | A survey and proposed framework on the soft biometrics technique for human identification in intelligent video surveillance system | |
| CN103927532B (en) | Person's handwriting method for registering based on stroke feature | |
| CN104036276A (en) | Face recognition method and device | |
| Lian et al. | Non-rigid 3D shape retrieval using multidimensional scaling and bag-of-features | |
| Liu et al. | Automatic gait recognition from a distance | |
| JP2009503721A (en) | Fingerprint aligning method and apparatus | |
| CN105117712A (en) | Single-sample human face recognition method compatible for human face aging recognition | |
| Vij et al. | Learning minutiae neighborhoods: A new binary representation for matching fingerprints | |
| CN106295649A (en) | Target identification method based on contour features | |
| CN103870812A (en) | Method and system for acquiring palmprint image | |
| Wang | Automatic extraction of building outline from high resolution aerial imagery | |
| CN105469402A (en) | Automobile part identification method based on space shape context characteristic | |
| CN104392216A (en) | Three-dimensional face recognition method for door lock | |
| CN110942077A (en) | Feature line extraction method based on weight local change degree and L1 median optimization | |
| CN103886303A (en) | Palmprint recognition method and device | |
| CN105404883B (en) | A kind of heterogeneous three-dimensional face identification method | |
| Pflug et al. | Robust localization of ears by feature level fusion and context information | |
| Berretti et al. | 3D partial face matching using local shape descriptors | |
| KR101528757B1 (en) | Texture-less object recognition using contour fragment-based features with bisected local regions | |
| Nikkam et al. | A key point selection shape technique for content based image retrieval system | |
| Ding et al. | A novel 3D ear identification approach based on sparse representation | |
| Li et al. | Learning weighted sparse representation of encoded facial normal information for expression-robust 3D face recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150304 |