CN105241811A - Multilevel focusing automatic image acquisition method and system thereof - Google Patents
Multilevel focusing automatic image acquisition method and system thereof Download PDFInfo
- Publication number
- CN105241811A CN105241811A CN201510641966.8A CN201510641966A CN105241811A CN 105241811 A CN105241811 A CN 105241811A CN 201510641966 A CN201510641966 A CN 201510641966A CN 105241811 A CN105241811 A CN 105241811A
- Authority
- CN
- China
- Prior art keywords
- focusing
- image
- target
- length
- layer
- 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.)
- Granted
Links
Landscapes
- Microscoopes, Condenser (AREA)
- Automatic Focus Adjustment (AREA)
Abstract
The invention provides a multilevel focusing automatic image acquisition method and a system thereof. The method comprises the following steps: focusing a counting plate according to a preset searching range, finding a first focusing surface, carrying out image acquisition on the first focusing surface to obtain a first target image, acquiring a focusing step length, setting image acquisition layers, respectively acquiring images of all the image acquisition layers to obtain a second target image group, fusing the first target image with images in the second target image, removing redundant targets and unclear targets, and automatically identifying and classifying residual targets to obtain a sample target classification detection result. Multi-focusing is adopted in the whole process to obtain different target images, and the different target images are fused to realize accurate image acquisition of a sample with high content of impurities, so targets in the sample can be accurately identified and counted.
Description
Technical field
The present invention relates to acquisition technology field, particularly relate to multi-level focusing and automatically adopt drawing method and system.
Background technology
In modern medical techniques field, in order to check that patient condition needs to carry out multiple project detection usually, have to relate to greatly in these test items and detect from collecting sample with it patient, such as common stool detects.
Before visible component detection is carried out to these samples, generally need the operation adopting the equipment producing pattern detection liquid to dilute sample, filter and sample thus the suspension obtained for visible component detection.Then be filled with in tally by suspension, microscope amplifies sample in tally, and image collecting device carries out image acquisition to sample, and pattern recognition device carries out target identification to the image gathered, thus obtains testing result.
Above-mentioned sample has polytype, and in the suspension (sample suspensions of such as defecating) of some sample, impurity is more, and density and the size of various target are different, and target to be detected is randomly dispersed in suspension.Be filled with by suspension after in tally, target to be checked can not sink to bottom tally completely, sinks to the target bottom tally completely, and owing to varying in size, focussing plane is also inconsistent.When image collecting device carries out focusing bat figure to sample to be tested, can only focus on a part of target, other is not positioned at conplane target cannot complete focusing.Cause in the picture of shooting, partial target is clear, and partial target is fuzzy.Some targets cannot photograph, and cannot well complete target identification and counting.
Summary of the invention
Based on this, be necessary for generally the automatic figure of adopting mode cannot to impure problem of accurately adopting figure compared with multisample, there is provided a kind of multi-level focusing automatically to adopt drawing method and system, realize accurately adopting figure to impure comparatively multisample, with accurately to target identification and counting in sample.
A kind of multi-level focusing adopts drawing method automatically, comprises step:
Focus on tally according to preset search scope, search the first focusing surface, carry out image acquisition to described first focusing surface, obtain first object image, wherein, described tally is filled with sample suspensions;
Obtain focusing step-length;
According to described focusing step-length, figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, obtains the second target image group;
Acquired target image is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result, wherein, described acquired target image comprises the image in described first object image and described second target image group.
A kind of multi-level focusing adopts drawing system automatically, comprising:
First object image collection module, for focusing on tally according to preset search scope, searches the first focusing surface, carries out image acquisition to described first focusing surface, and obtain first object image, wherein, described tally is filled with sample suspensions;
Focusing step-length acquisition module, for obtaining focusing step-length;
Second target image group acquisition module, for according to described focusing step-length, sets and adopts figure layer, gather the image adopting figure layer described in each respectively, obtain the second target image group;
Fusion Module, for acquired target image is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result, wherein, described acquired target image comprises the image in described first object image and described second target image group.
The present invention focuses at many levels and automatically adopts drawing method and system, according to preset search scope, tally is focused on, search the first focusing surface, image acquisition is carried out to described first focusing surface, obtain first object image, obtain focusing step-length, according to described focusing step-length, figure layer is adopted in setting, gather the image adopting figure layer described in each respectively, obtain the second target image group, by the image co-registration in described first object image and described second target image group, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.In whole process, adopt multi-focusing to obtain different target image, and fusions realization is carried out to different target image accurately figure is adopted to impure comparatively multisample, can accurately to target identification and counting in sample.
Accompanying drawing explanation
Fig. 1 is that the present invention focuses on the schematic flow sheet automatically adopting drawing method first embodiment at many levels;
Fig. 2 is that the present invention focuses on the schematic flow sheet automatically adopting drawing method second embodiment at many levels;
Fig. 3 is that the present invention focuses on the structural representation automatically adopting drawing system first embodiment at many levels;
Fig. 4 is that the present invention focuses on the structural representation automatically adopting drawing system second embodiment at many levels.
Embodiment
As shown in Figure 1, a kind of multi-level focusing adopts drawing method automatically, comprises step:
S200: focus on tally according to preset search scope, searches the first focusing surface, carries out image acquisition to described first focusing surface, and obtain first object image, wherein, described tally is filled with sample suspensions.
Preset search scope is the value range preset based on detection demand, for searching of the first focusing surface, we by self-focusing equipment, such as, can use self-focusing microscope to search the first focusing surface, carry out image acquisition, obtain first object image.Wherein in a concrete operations example, non-essential, some preliminary works are carried out at execution step S200, sample is such as first needed to gather from patient with it, afterwards by Sample Dilution, make suspension, then sample suspensions is filled with tally, under tally is placed into microscope, by microscope, sample suspensions on tally is amplified.Above-mentioned focusing upwards can carry out from bottom tally, also can carry out bottom tally from the surface of sample suspensions.
S400: obtain focusing step-length.
Focusing step-length can adopt various ways to obtain, such as can calculate according to the type of current detection sample suspensions and detection demand etc. and obtain, also can be directly read to preset the acquisition of focusing step-length, preset focusing step-length and preset based on historical empirical data.
Wherein in an embodiment, step S400 is specially: the image parameter detecting all kinds of target in first object image, according to the image parameter of target all kinds of in first object image, determines step-length of focusing.
The image parameter of target specifically can comprise target sharpness, target morphology and target sizes, according to these image parameters, obtains focusing step-length.Further, can be weighted for target sharpness, target morphology and target sizes, then according to weighing computation results and default detection demand, obtain focusing step-length.Adopt weighted calculation mode, consider the impact of different images parameter on focusing step-length, thus can accurately obtain focusing step-length, to obtain target image clearly in subsequent operation.
Wherein in an embodiment, step S400 is specially: read the focusing step-length preset.The focusing step-length preset presets, the size according to each target in first object image of its setting, default detection demand and historical empirical data.
S600: according to described focusing step-length, figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, obtains the second target image group.
Just as described above, in sample suspensions, the density of various target is in different size, and target to suspend or in bottom sedimentation by diverse location in suspension, if the single figure tomographic image of simple shooting, can cause having target take unintelligible or shooting less than.To this, here, according to described focusing step-length, figure layer is adopted in setting, adopts figure layer and can be provided with multiple, gather the image that each adopts figure layer respectively, obtain the second target image group.
S800: acquired target image is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result, wherein, acquired target image comprises the image in described first object image and described second target image group.
Image in first object image and the second target image group exists that some target is unintelligible, some target is by repeatedly repeated acquisition, to this, here the image (acquired target image) in first object image and described second target image group is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.Above-mentioned removal redundancy object and unintelligible target can adopt related software or image-data processing apparatus to operate.For Motion parameters and classification, the neural network classifier based on morphological image feature trained can be utilized to process.
The present invention focuses at many levels and automatically adopts drawing method, according to preset search scope, tally is focused on, search the first focusing surface, image acquisition is carried out to described first focusing surface, obtain first object image, obtain focusing step-length, according to described focusing step-length, figure layer is adopted in setting, gather the image adopting figure layer described in each respectively, obtain the second target image group, by the image co-registration in described first object image and described second target image group, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.In whole process, adopt multi-focusing to obtain different target image, and fusions realization is carried out to different target image accurately figure is adopted to impure comparatively multisample, can accurately to target identification and counting in sample.
Wherein in an embodiment, described according to described focusing step-length, figure layer is adopted in setting, and gather the image adopting figure layer described in each respectively, the step obtaining the second target image group specifically comprises:
With the position of described first focusing surface for reference position, figure interval is adopted respectively with extended the presetting of upper and lower both direction, adopt in figure interval described presetting, according to described focusing step-length, figure layer is adopted in setting, wherein, described presetting adopts the interval interval be less than to described sample suspensions surface bottom tally of figure;
Gather the image adopting figure layer described in each, obtain the second target image group.
In the present embodiment, first the position of the first focusing surface is obtained, afterwards with the first focusing surface position for benchmark, near the first focusing surface position, extended the presetting of upper and lower both direction adopts figure interval, adopt in figure interval according to focusing step-length default, figure layer is adopted in setting, gathers the image that each adopts figure layer, obtains the second target image group.Such as, we first can obtain the first focusing surface position, afterwards with the first focusing surface position for benchmark, respectively set 5 in the first upper and lower both direction in focusing surface position according to focusing step-length and adopt figure layer, namely now obtain the image that 10 are adopted figure layer, namely the second target image group comprises the image that these 10 are adopted figure layer.It is pointed out that in the present embodiment, presetting and adopting figure interval is plan setting in advance good, its bottom tally to the interval on sample suspensions surface.Further, presetting and adopting figure interval is a smaller value, namely the first focusing surface position up and down near position set and adopt figure layer.
Wherein in an embodiment, described according to described focusing step-length, figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, also comprises after obtaining the second target image group step:
Read and preset the second focusing step-length, wherein, described second focusing step-length deterministic process of presetting is specially, gather and be filled with in the sample suspensions of tally the primary importance falling to tally bottom target focus layer and the second place being suspended in tally top target focus layer, the described primary importance that the multiple sample suspensions of repeated acquisition is corresponding and the described second place, statistics obtains primary importance group and second place group, according to described primary importance group and described second place group, obtain described default second focusing step-length;
At the station acquisition image of step-length of focusing at a distance of described default second from described first focusing surface, obtain the 3rd target image;
Described acquired target image to be merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, the step obtaining sample object classification and Detection result is specially:
Image in described first object image, described second target image group and described 3rd target image are merged, removes redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.
Preset the second focusing step-length and be different from aforesaid default focusing step-length, specifically, presetting the second focusing step-length is the preset value determined according to test of many times, this process of the test is specially, first, gather and be filled with in the sample suspensions of tally the primary importance falling to tally bottom target focus layer and the second place being suspended in tally top target focus layer, afterwards, the primary importance that the multiple sample suspensions of repeated acquisition is corresponding and the second place, statistics obtains primary importance group and second place group, finally, according to primary importance group and second place group, obtain and preset the second focusing step-length, in above-mentioned process of the test, primary importance and the second place can adopt automatic focus mode to determine, the multiple sample suspensions chosen can be the sample suspensions of same item type (be such as blood sample suspension or be stool sample suspensions).The mean value of the second place in the mean value of primary importance in primary importance group and second place group can be calculated after obtaining primary importance group and second place group, again the mean value of primary importance and the mean value of the second place subtracted each other and takes absolute value, obtaining and preset the second focusing step-length.After obtaining the second default focusing step-length on the first focusing surface, image is gathered according to presetting the second focusing step-length, obtain the 3rd target image, now gather and obtained first object image, the second target image group and the 3rd target image, carry out successive image fusing stage, these three kinds of images are being merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.Again consider that target density is different, target is suspended in sample suspensions diverse location easily to be affected and adopts the problem that partial target in figure image is unintelligible or cannot photograph, and the sample classification testing result obtained after making final fusion treatment is more accurate.
Wherein in an embodiment, described according to described focusing step-length, figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, obtains the second target image group step and specifically comprise:
With bottom tally for reference position, in described sample suspensions surface region bottom described tally, according to described focusing step-length, figure layer is adopted in setting at equal intervals;
Gather the image adopting figure layer described in each respectively, obtain the second target image group.
In instantiation, according to the focusing step-length determined of pre-treatment, from bottom tally for benchmark from bottom to top (from bottom tally to near microscopical direction) at equal intervals setting adopt figure layer, gather the image adopting figure layer described in each respectively, obtain the second target image group.Step-length of here focusing can be understood as a fixing numerical value, in the zone distance on suspension surface bottom tally, sets at equal intervals and multiplely adopts figure layer.
As shown in Figure 2, wherein in an embodiment, also comprise after step S200:
S300: fog-level detection is carried out to all targets in described first object image, detects in described first object image whether there is unintelligible target image.
Fog-level detection is carried out to all targets in first object image, when there is unintelligible target image in first object image, explanation cannot based on the classification and Detection of first object image realization to sample object, the image again carrying out focusing the different layer of collection is needed to process, to this, enter step S400; When there is not unintelligible target image in first object image, explanation can according to the classification and Detection of first object image realization to sample object, for improving the efficiency of sample object classification and Detection, directly carrying out Motion parameters and classification, obtaining the operation of sample object classification and Detection result.
In addition, as shown in Figure 3, automatically adopt drawing method based on above-mentioned multi-level focusing, the present invention also provides a kind of multi-level focusing automatically to adopt drawing system, comprising:
First object image collection module 100, for focusing on tally according to preset search scope, searches the first focusing surface, carries out image acquisition to described first focusing surface, obtains first object image;
Focusing step-length acquisition module 200, for obtaining focusing step-length;
Second target image group acquisition module 300, for according to described focusing step-length, sets and adopts figure layer, gather the image adopting figure layer described in each respectively, obtain the second target image group;
Fusion Module 400, for acquired target image is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result, wherein, described acquired target image comprises the image in described first object image and described second target image group.
The present invention focuses at many levels and automatically adopts drawing system, first object image collection module 100 focuses on tally according to preset search scope, search the first focusing surface, image acquisition is carried out to described first focusing surface, obtain first object image, focusing step-length acquisition module 200 obtains focusing step-length, second target image group acquisition module 300 is according to described focusing step-length, figure layer is adopted in setting, gather the image adopting figure layer described in each respectively, obtain the second target image group, Fusion Module 400 is by the image co-registration in described first object image and described second target image group, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.In whole process, adopt multi-focusing to obtain different target image, and fusions realization is carried out to different target image accurately figure is adopted to impure comparatively multisample, can accurately to target identification and counting in sample.
Wherein in an embodiment, described focusing step-length acquisition module 200, specifically for detecting the image parameter of all kinds of target in first object image, according to the image parameter of target all kinds of in first object image, determines step-length of focusing.Wherein, image parameter comprises target sharpness, target morphology and target sizes.
Wherein in an embodiment, described focusing step-length acquisition module 200 is specifically for reading default focusing step-length.The focusing step-length preset presets, the size according to each target in first object image of its setting, default detection demand and historical empirical data.
Wherein in an embodiment, described second target image group acquisition module 300 specifically comprises:
First adopts figure layer setup unit, for with the position of described first focusing surface for reference position, figure interval is adopted respectively with extended the presetting of upper and lower both direction, adopt in figure interval default, according to described focusing step-length, figure layer is adopted in setting, and wherein, described presetting adopts the interval interval be less than to described sample suspensions surface bottom tally of figure;
First collecting unit, for gathering the image adopting figure layer described in each, obtains the second target image group.
Wherein in an embodiment, described multi-level focusing is automatically adopted drawing system and is also comprised:
Second focusing step-length acquisition module, for reading default second focusing step-length, wherein, described second focusing step-length deterministic process of presetting is specially, gather and be filled with in the sample suspensions of tally the primary importance falling to tally bottom target focus layer and the second place being suspended in tally top target focus layer, the described primary importance that the multiple sample suspensions of repeated acquisition is corresponding and the described second place, statistics obtains primary importance group and second place group, according to described primary importance group and described second place group, obtain described default second focusing step-length;
3rd target image acquisition module, for the station acquisition image in step-length of focusing at a distance of described default second from described first focusing surface, obtains the 3rd target image;
Described Fusion Module is used for the image in described first object image, described second target image group and described 3rd target image to merge, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.
Wherein in an embodiment, described second target image group acquisition module 300 specifically comprises:
Second adopts figure layer setup unit, for bottom tally for reference position, in described sample suspensions surface region bottom tally, according to described focusing step-length, figure layer is adopted in setting at equal intervals;
Second collecting unit, for gathering the image adopting figure layer described in each respectively, obtains the second target image group.
As shown in Figure 4, wherein in an embodiment, described multi-level focusing is automatically adopted drawing system and is also comprised:
Detection module 500, for carrying out fog-level detection to all targets in described first object image, detects in described first object image whether there is unintelligible target image.
In order to further explain that the present invention focuses on the technical scheme of automatically adopting drawing method and system and the beneficial effect brought thereof at many levels, will, for sample of defecating, adopt two examples to introduce whole process in detail in detail below.
Example one:
Step one: make stool sample suspensions.
Step 2: stool sample suspensions is filled with tally.
Step 3: utilize microscope automatically to amplify the sample on tally.
Step 4: automatic focus is upwards carried out in the hunting zone according to presetting from tally bottom surface, finds first focusing surface, carries out image acquisition and obtain first object image and record the first focusing surface position.
Step 5: fog-level detection being carried out to targets all in first object image and obtains the first testing result, when there is unintelligible target image in first object image, entering next step; When there is not unintelligible target image in first object image, directly carrying out Motion parameters and classification, obtaining the operation of sample object classification and Detection result.
Step 6: detect the sharpness of each target in first object image, form and size, by being weighted this few class parameter and with reference to testing requirement, determining the first focusing step-length.
Step 7: respectively gather 5 sub-pictures up and down near the first focusing surface, the focal position of every sub-picture focuses on and is spaced apart the first focusing step-length.Gather this 10 sub-picture respectively and obtain the second image sets.
Step 8: read and preset the second focusing step-length.
Step 9: regulate microscope on the first focusing surface top according to presetting the second focusing step-length, and gather image, obtain the 3rd image.
Step 10: merge the image in first object image and the second target image group and the 3rd image, removes redundancy object and unintelligible target, then automatically identifies residue target and classifies, thus obtaining sample object classification and Detection result.
Example two:
Step one: make stool sample suspensions.
Step 2: stool sample suspensions is filled with tally.
Step 3: utilize microscope automatically to amplify the sample on tally.
Step 4: to carrying out automatic focus bottom tally and image acquisition obtains first object image;
Step 5: fog-level detection being carried out to targets all in first object image and obtains the first testing result, when there is unintelligible target image in first object image, entering next step; When there is not unintelligible target image in first object image, directly carrying out Motion parameters and classification, obtaining the operation of sample object classification and Detection result.
Step 6: read the default fixing focusing step-length L and Cai Tu number of plies n that microscope regulates, bottom tally the step-length L of the fixing focusing in interval from the bottom to top respectively collect specimen picture obtain second, third ... until n-th layer target image, preset fixing focusing step-length L and preset based on the size of target each in first object image, detection demand and historical empirical data.
Step 7: to first, second ... carry out image automatic identification and differential count with the n-th target image, add up and obtain sample to be tested target classification testing result after removing repetition object count.
The above embodiment only have expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be construed as limiting the scope of the patent.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. multi-level focusing adopts a drawing method automatically, it is characterized in that, comprises step:
Focus on tally according to preset search scope, search the first focusing surface, carry out image acquisition to described first focusing surface, obtain first object image, wherein, described tally is filled with sample suspensions;
Obtain focusing step-length;
According to described focusing step-length, figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, obtains the second target image group;
Acquired target image is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result, wherein, described acquired target image comprises the image in described first object image and described second target image group.
2. multi-level focusing according to claim 1 adopts drawing method automatically, it is characterized in that, the described step obtaining focusing step-length is specially:
Detect the image parameter of all kinds of target in described first object image, according to the image parameter of all kinds of target in described first object image, obtain focusing step-length.
3. multi-level focusing according to claim 1 and 2 adopts drawing method automatically, it is characterized in that, described according to described focusing step-length, and figure layer is adopted in setting, and gather the image adopting figure layer described in each respectively, the step obtaining the second target image group specifically comprises:
With the position of described first focusing surface for reference position, figure interval is adopted respectively with extended the presetting of upper and lower both direction, adopt in figure interval described presetting, according to described focusing step-length, figure layer is adopted in setting, wherein, described presetting adopts the interval interval be less than to described sample suspensions surface bottom tally of figure;
Gather the image adopting figure layer described in each, obtain the second target image group.
4. multi-level focusing according to claim 3 adopts drawing method automatically, it is characterized in that, described according to described focusing step-length, and figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, also comprises after obtaining the second target image group step:
Read and preset the second focusing step-length, wherein, described second focusing step-length deterministic process of presetting is specially, gather and be filled with in the sample suspensions of tally the primary importance falling to tally bottom target focus layer and the second place being suspended in tally top target focus layer, the described primary importance that the multiple sample suspensions of repeated acquisition is corresponding and the described second place, statistics obtains primary importance group and second place group, according to described primary importance group and described second place group, obtain described default second focusing step-length;
At the station acquisition image of step-length of focusing at a distance of described default second from described first focusing surface, obtain the 3rd target image;
Described acquired target image to be merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, the step obtaining sample object classification and Detection result is specially:
Image in described first object image, described second target image group and described 3rd target image are merged, removes redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.
5. multi-level focusing according to claim 1 adopts drawing method automatically, it is characterized in that, described according to described focusing step-length, and figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, also comprises after obtaining the second target image group step:
Read and preset the second focusing step-length, wherein, described second focusing step-length deterministic process of presetting is specially, gather and be filled with in the sample suspensions of tally the primary importance falling to tally bottom target focus layer and the second place being suspended in tally top target focus layer, the described primary importance that the multiple sample suspensions of repeated acquisition is corresponding and the described second place, statistics obtains primary importance group and second place group, according to described primary importance group and described second place group, obtain described default second focusing step-length;
At the station acquisition image of step-length of focusing at a distance of described default second from described first focusing surface, obtain the 3rd target image;
Described acquired target image to be merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, the step obtaining sample object classification and Detection result is specially:
Image in described first object image, described second target image group and described 3rd target image are merged, removes redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result.
6. multi-level focusing according to claim 1 adopts drawing method automatically, it is characterized in that, the described step obtaining focusing step-length is specially:
Read and preset focusing step-length.
7. the multi-level focusing according to claim 1 or 6 adopts drawing method automatically, it is characterized in that, described according to described focusing step-length, and figure layer is adopted in setting, gathers the image adopting figure layer described in each respectively, obtains the second target image group step and specifically comprise:
With bottom tally for reference position, in described sample suspensions surface region bottom described tally, according to described focusing step-length, figure layer is adopted in setting at equal intervals;
Gather the image adopting figure layer described in each respectively, obtain the second target image group.
8. multi-level focusing adopts a drawing system automatically, it is characterized in that, comprising:
First object image collection module, for focusing on tally according to preset search scope, searches the first focusing surface, carries out image acquisition to described first focusing surface, and obtain first object image, wherein, described tally is filled with sample suspensions;
Focusing step-length acquisition module, for obtaining focusing step-length;
Second target image group acquisition module, for according to described focusing step-length, sets and adopts figure layer, gather the image adopting figure layer described in each respectively, obtain the second target image group;
Fusion Module, for acquired target image is merged, remove redundancy object and unintelligible target, and to residue Motion parameters and classification, obtain sample object classification and Detection result, wherein, described acquired target image comprises the image in described first object image and described second target image group.
9. multi-level focusing according to claim 8 adopts drawing system automatically, it is characterized in that, described second target image group acquisition module specifically comprises:
First adopts figure layer setup unit, for with the position of described first focusing surface for reference position, figure interval is adopted respectively with extended the presetting of upper and lower both direction, adopt in figure interval described presetting, according to described focusing step-length, figure layer is adopted in setting, and wherein, described presetting adopts the interval interval be less than to described sample suspensions surface bottom tally of figure;
First collecting unit, for gathering the image adopting figure layer described in each, obtains the second target image group.
10. multi-level focusing according to claim 8 adopts drawing system automatically, it is characterized in that, described second target image group acquisition module specifically comprises:
Second adopts figure layer setup unit, for bottom tally for reference position, in described sample suspensions surface region bottom described tally, according to described focusing step-length, figure layer is adopted in setting at equal intervals;
Second collecting unit, for gathering the image adopting figure layer described in each respectively, obtains the second target image group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510641966.8A CN105241811B (en) | 2015-09-30 | 2015-09-30 | Multi-level focus adopts drawing method and system automatically |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510641966.8A CN105241811B (en) | 2015-09-30 | 2015-09-30 | Multi-level focus adopts drawing method and system automatically |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105241811A true CN105241811A (en) | 2016-01-13 |
| CN105241811B CN105241811B (en) | 2018-10-23 |
Family
ID=55039533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510641966.8A Active CN105241811B (en) | 2015-09-30 | 2015-09-30 | Multi-level focus adopts drawing method and system automatically |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105241811B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106019557A (en) * | 2016-08-17 | 2016-10-12 | 珠海科域生物工程有限公司 | Multi-layer photographing method and photographing system for microscopic examination |
| CN110763679A (en) * | 2019-10-31 | 2020-02-07 | 湖南爱威医疗科技有限公司 | Image acquisition method and device, microscope system and computer readable storage medium |
| CN110927158A (en) * | 2019-10-31 | 2020-03-27 | 湖南爱威医疗科技有限公司 | Image acquisition method and device, microscope system and computer readable storage medium |
| CN112241953A (en) * | 2020-10-22 | 2021-01-19 | 江苏美克医学技术有限公司 | Sample image fusion method and device based on multi-focus image fusion and HDR algorithm |
| CN112986239A (en) * | 2021-02-05 | 2021-06-18 | 爱威科技股份有限公司 | Layered image collection method and device, computer equipment and storage medium |
| CN112986141A (en) * | 2021-02-05 | 2021-06-18 | 爱威科技股份有限公司 | Layered image collection method and device, computer equipment and storage medium |
| CN112986141B (en) * | 2021-02-05 | 2024-04-30 | 爱威科技股份有限公司 | Hierarchical image acquisition method, hierarchical image acquisition device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6438261B1 (en) * | 1998-09-03 | 2002-08-20 | Green Vision Systems Ltd. | Method of in-situ focus-fusion multi-layer spectral imaging and analysis of particulate samples |
| US20070286517A1 (en) * | 2006-06-13 | 2007-12-13 | Chung-Ang University Industry Academic Cooperation Foundation | Method and apparatus for multifocus digital image restoration using image integration technology |
| CN101615289A (en) * | 2009-08-05 | 2009-12-30 | 北京优纳科技有限公司 | The three-dimensional acquisition of biopsy tissues and fusion method of multilayer images |
| CN101630061A (en) * | 2009-08-17 | 2010-01-20 | 公安部物证鉴定中心 | Optical confocal three-dimensional data acquisition system of tool traces and acquisition method thereof |
| CN202600251U (en) * | 2012-04-01 | 2012-12-12 | 潍坊学院 | Microscopic image fusion system |
-
2015
- 2015-09-30 CN CN201510641966.8A patent/CN105241811B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6438261B1 (en) * | 1998-09-03 | 2002-08-20 | Green Vision Systems Ltd. | Method of in-situ focus-fusion multi-layer spectral imaging and analysis of particulate samples |
| US20070286517A1 (en) * | 2006-06-13 | 2007-12-13 | Chung-Ang University Industry Academic Cooperation Foundation | Method and apparatus for multifocus digital image restoration using image integration technology |
| CN101615289A (en) * | 2009-08-05 | 2009-12-30 | 北京优纳科技有限公司 | The three-dimensional acquisition of biopsy tissues and fusion method of multilayer images |
| CN101630061A (en) * | 2009-08-17 | 2010-01-20 | 公安部物证鉴定中心 | Optical confocal three-dimensional data acquisition system of tool traces and acquisition method thereof |
| CN202600251U (en) * | 2012-04-01 | 2012-12-12 | 潍坊学院 | Microscopic image fusion system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106019557A (en) * | 2016-08-17 | 2016-10-12 | 珠海科域生物工程有限公司 | Multi-layer photographing method and photographing system for microscopic examination |
| CN110763679A (en) * | 2019-10-31 | 2020-02-07 | 湖南爱威医疗科技有限公司 | Image acquisition method and device, microscope system and computer readable storage medium |
| CN110927158A (en) * | 2019-10-31 | 2020-03-27 | 湖南爱威医疗科技有限公司 | Image acquisition method and device, microscope system and computer readable storage medium |
| CN112241953A (en) * | 2020-10-22 | 2021-01-19 | 江苏美克医学技术有限公司 | Sample image fusion method and device based on multi-focus image fusion and HDR algorithm |
| CN112241953B (en) * | 2020-10-22 | 2023-07-21 | 江苏美克医学技术有限公司 | Sample image fusion method and device based on multi-focus image fusion and HDR algorithm |
| CN112986239A (en) * | 2021-02-05 | 2021-06-18 | 爱威科技股份有限公司 | Layered image collection method and device, computer equipment and storage medium |
| CN112986141A (en) * | 2021-02-05 | 2021-06-18 | 爱威科技股份有限公司 | Layered image collection method and device, computer equipment and storage medium |
| CN112986141B (en) * | 2021-02-05 | 2024-04-30 | 爱威科技股份有限公司 | Hierarchical image acquisition method, hierarchical image acquisition device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105241811B (en) | 2018-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3785021B1 (en) | System and method for performing automated analysis of air samples | |
| JP7200113B2 (en) | Systems and methods for training and applying defect classifiers on wafers with deeply stacked layers | |
| JP6490211B2 (en) | Wafer defect detection | |
| CN105241811A (en) | Multilevel focusing automatic image acquisition method and system thereof | |
| US9489562B2 (en) | Image processing method and apparatus | |
| JP3822242B2 (en) | Method and apparatus for evaluating slide and sample preparation quality | |
| CN105139386B (en) | A kind of image processing method of fast automatic detecting electric connector solder joint defective work | |
| CN108352339A (en) | Adaptive automatic defect classification | |
| CN102637258B (en) | Method for creating online surface quality detection system defect library | |
| US7283659B1 (en) | Apparatus and methods for searching through and analyzing defect images and wafer maps | |
| JPH10508709A (en) | Device for detecting air bubbles in cover slip adhesive | |
| CN104021382A (en) | Eye image collection method and system | |
| CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
| CN109462999B (en) | Visual inspection method based on learning through data balance and visual inspection device using same | |
| CN111801783B (en) | Jammer mining for novel defect discovery | |
| CN109492647A (en) | A kind of power grid robot barrier object recognition methods | |
| JP3272036B2 (en) | Optical inspection method and device for defects on object surface | |
| JP5530126B2 (en) | Three-dimensional cell image analysis system and three-dimensional cell image analyzer used therefor | |
| JP2014157158A (en) | Cell observation method, three-dimensional cell image analysis system, and three-dimensional cell image analyzer used therefor | |
| WO2023031622A1 (en) | System and method for identifying and counting biological species | |
| JP2005315792A (en) | Defect inspecting/classifying apparatus | |
| CN117589633B (en) | Grain impurity detection device and method | |
| JPH0513570B2 (en) | ||
| JP2016137474A (en) | Inspection method and inspection device for hollow fiber module | |
| KR101669075B1 (en) | System and method for inspecting defects |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |