CN113837291A - Identification and positioning method and system based on backlight module and multi-template matching - Google Patents
Identification and positioning method and system based on backlight module and multi-template matching Download PDFInfo
- Publication number
- CN113837291A CN113837291A CN202111135769.0A CN202111135769A CN113837291A CN 113837291 A CN113837291 A CN 113837291A CN 202111135769 A CN202111135769 A CN 202111135769A CN 113837291 A CN113837291 A CN 113837291A
- Authority
- CN
- China
- Prior art keywords
- module
- template
- image
- sole
- identified
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000003706 image smoothing Methods 0.000 claims abstract description 7
- 239000000463 material Substances 0.000 claims description 27
- 230000005540 biological transmission Effects 0.000 claims description 17
- 238000005286 illumination Methods 0.000 claims description 16
- 238000009499 grossing Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 229910000838 Al alloy Inorganic materials 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006698 induction Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 101100311458 Lytechinus variegatus SUM-1 gene Proteins 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a recognition and positioning method and a system based on matching of a backlight module and multiple templates, wherein the recognition and positioning method comprises the following steps: acquiring an image of a target area based on an image acquisition module to obtain a sole image to be identified; carrying out image smoothing processing on the sole image to be identified through an image processing module to obtain template contour information of the sole image to be identified; and matching the outline information of the sole image template to be identified in a preset sole template base based on the outline information of the sole image template to be identified to obtain sole information corresponding to the outline information of the sole image template to be identified. In the automatic production of the shoe making industry, after products are sent into the backlight module, the machine vision algorithm is utilized, the backlight module is matched, the multi-template matching algorithm is adopted, the products with different models are quickly and accurately identified and positioned, the operation is simple, and the technical cost is low.
Description
Technical Field
The invention relates to the field of machine vision, in particular to a recognition and positioning method and system based on matching of a backlight module and multiple templates.
Background
In the automatic production of the shoe making industry, soles are divided into left feet and right feet with different models and sizes, the left foot template and the right foot template with each model and size are easy to establish, each template can be integrated in a template library, but the template with the highest matching degree is selected as a result when being called for matching, only the number-th file in the template library can be obtained, but labels cannot be added to the templates, a deep learning algorithm in the field of artificial intelligence is adopted, the labels can be added to the trained templates, the hardware environment needs to be matched when deep learning is used, the trained samples are difficult to collect in large quantities, and the operation is complex and the cost is high.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a recognition and positioning method and a system based on backlight module and multi-template matching.
In order to solve the above technical problems, the present invention is solved by the following technical solutions.
A recognition and positioning method based on backlight module and multi-template matching is characterized by comprising the following steps:
acquiring an image of a target area based on an image acquisition module to obtain a sole image to be identified;
carrying out image smoothing processing on the sole image to be identified through an image processing module to obtain template contour information of the sole image to be identified;
and matching the outline information of the sole image template to be identified in a preset sole template base based on the outline information of the sole image template to be identified to obtain sole information corresponding to the outline information of the sole image template to be identified.
As an implementation mode, the sole template library is provided with a plurality of levels of catalogues, wherein the first level catalog is the sole shoe type, the second level catalog is the sole size, the third level catalog is the left foot and the right foot, and the sole template library is updated and supplemented based on historical sole information.
As one implementation, the templates under each level of directory are traversed one by one and recorded in the template array.
As an implementation mode, when the first-level templates are matched, matched shoe type template information is obtained from the template array, the corresponding first-level template serial number is obtained, the size template information of the corresponding shoe type is obtained through second-level template matching, the corresponding second-level template serial number is obtained, finally, the left and right foot template information is obtained through third-level template matching, the corresponding third-level template serial number is obtained, and sole information is obtained based on the obtained third-level template serial number matching.
As an implementable mode, the image processing module performs iterative processing and Gaussian smoothing on the sole image to be recognized, removes noise and obtains template contour information of the sole image to be recognized.
As an implementation mode, the image acquisition module comprises an image acquisition module and a backlight module, the image acquisition module is arranged at the top of the backlight module, the image acquisition module is fixedly connected with the image processing module, the bottom of the backlight module is provided with a transmission module, a material induction module and an illumination module, the illumination module is arranged under the transmission module and corresponds to the image acquisition module in position, the material induction module and the illumination module are connected with the main control module, and the top of the backlight module is fixedly connected with the bottom of the backlight module.
As an implementable manner, the image acquisition module comprises a camera, a camera support and a camera lens;
the camera bracket is fixedly arranged at the top of the backlight module;
the camera is arranged on the camera bracket;
the camera lens is connected to the camera.
As an implementation manner, the lighting module is a surface light source.
As an embodiment, the transport module is a transparent conveyor belt.
A recognition and positioning system based on backlight module and multi-template matching comprises:
the image acquisition module is used for acquiring an image of the target area to obtain a sole image to be identified;
the image processing module is used for carrying out image smoothing processing on the sole image to be identified to obtain the template outline of the sole image to be identified, matching the template outline information of the sole image to be identified in a preset sole template base based on the template outline information of the sole image to be identified to obtain the sole information corresponding to the template outline information of the sole image to be identified, wherein,
the image acquisition module comprises an image acquisition module and a backlight module, the image acquisition module is arranged at the top of the backlight module, the image acquisition module is fixedly connected with the backlight module, the image acquisition module is connected with the image processing module, the bottom of the backlight module is provided with a transmission module, a material sensing module and a lighting module, the lighting module is arranged under the transmission module and corresponds to the position of the image acquisition module, the material sensing module and the lighting module are connected with the main control module, and the top of the backlight module is fixedly connected with the bottom of the backlight module.
Due to the adoption of the technical scheme, the invention has the remarkable technical effects that:
according to the identification and positioning method and system based on the matching of the backlight module and the multiple templates, provided by the embodiment of the invention, in the automatic production of the shoe manufacturing industry, the machine vision algorithm is utilized, the backlight module is matched, the multiple template matching algorithm is adopted, the quick and accurate identification and positioning of different types of products are realized, the operation is simple, and the technical cost is low.
The features and advantages of the present invention will be described in detail by embodiments in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of an identification and positioning method based on backlight module and multi-template matching according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an image acquisition module according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an image capture module according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a lighting module provided in an embodiment of the present invention;
fig. 5 is a schematic view of a backlight module base structure according to an embodiment of the invention.
Reference numbers in the drawings illustrate:
10. an image acquisition module; 11. a camera; 12. a camera support; 13. a camera lens; 20. a transport module; 21. a support plate; 22. a locking sleeve; 23. rotating the driving shaft; 24. rotating the driven shaft; 30. a material sensing module; 40. a drive module; 50. a lighting module; 60. provided is a machine platform.
Detailed Description
The present invention will be described in further detail with reference to examples, which are illustrative of the present invention and are not to be construed as being limited thereto.
In this embodiment, an identification and positioning method based on matching of a backlight module and multiple templates is provided, and referring to fig. 1, the process includes the following steps:
and S100, acquiring an image of the target area based on the image acquisition module to obtain a sole image to be identified.
In the embodiment of the present invention, the image acquisition module includes an image acquisition module 10 and a backlight module, where the image acquisition module 10 includes a camera 11, a camera bracket 12 and a camera lens 13, and records an image in a certain range through the camera 11, so as to generate target image information. The camera 11 is connected to the processing unit to perform corresponding data transmission, and performs image processing through an image processing module on the processing unit, specifically, the camera 11 may be connected to the processing unit in a wired or wireless manner to perform corresponding data transmission. The processing unit can be integrated into a processor in the camera, and can also be a processor in the central control equipment of the internet of things.
And S200, carrying out image smoothing on the sole image to be identified through an image processing module to obtain the template contour information of the sole image to be identified.
In this embodiment, the image processing module performs iterative processing on an image by using 7 layers of pyramids, performs gaussian smoothing on an original image, performs downsampling every time, changes the image into one fourth of the original image, performs upsampling once through inverse transformation, changes the image into the original image size, performs gaussian smoothing again to obtain a smooth edge image, sets an initial angle to be rad (0), controls an angle range to be rad (360), controls a rotation angle step size, searches once per rad (0.2), and jointly forms a search result determination matrix [101110] by using an image contrast and a component minimum size as a search object, and converts the search object into a coordinate under a rectangular coordinate system in a polar coordinate system to obtain a template profile.
In some embodiments, the sole is elongated due to expansion with heat and contraction with cold during baking, and the scaling factor is set according to the deformation of the sole during baking at high temperature for different time periods
The deformation proportional factor of the sole baked for 3 minutes at 100 ℃ is
The deformation scaling factor of the sole after being baked for 5 minutes is
The deformation scaling factor of the sole after being baked for 10 minutes is
The deformation scaling factor of the baking time of 20 minutes is
And selecting deformation variable scale factors under corresponding duration based on the sole baking time to perform contour scaling treatment, so as to obtain the deformed template contour.
And step S300, matching in a preset sole template base based on the outline information of the sole image template to be identified to obtain sole information corresponding to the outline information of the sole image template to be identified.
In the embodiment of the invention, the sole template library is established by adopting a multi-level catalog, the first-level catalog is a shoe type template, the second-level catalog is a size template, the third-level catalog is a left foot template and a right foot template, the template library is supplemented based on historical material information, and the template library comprises all template information of sole materials. The multi-level catalog management effectively obtains the catalog template corresponding to the template, and further facilitates the management of each level template under the catalog. And traversing the templates under each level of directory one by one and recording the templates in the template array. Matching the sole images to be identified, acquiring matched shoe type template information in the template array when the first-stage templates are matched, acquiring corresponding first-stage template serial numbers, acquiring size template information of corresponding shoe types through second-stage template matching, acquiring corresponding second-stage template serial numbers, acquiring left and right foot template information through third-stage template matching, acquiring corresponding third-stage template serial numbers, and acquiring sole information based on third-stage template serial number matching.
Specifically, the total number of the templates is SUM, the first grade A, B is two shoe types, the total number of the shoe type a templates is M, the total number of the shoe type B templates is N, that is, M + N is SUM; each shoe type comprises a second-level catalog of C-size templates and D-size templates, the total number of the C-size templates of the A-shoe type templates is M1, the total number of the D-size templates is M2, namely M1+ M2-M, the total number of the C-size templates of the corresponding B-shoe type templates is N1, and the total number of the D-size templates is N2, namely N1+ N2-N; each size template comprises two third-level catalogues of a left foot and a right foot, the total number of the left foot templates of the A-shoe type C size template is M11, the total number of the right foot templates of the A-shoe type C size template is M12, namely M11+ M12 equals M1, the number of the left foot templates of the same A-shoe type D size is M21, the number of the right foot templates is M22, M21+ M22 equals M2, the total number of the right foot templates of the B-shoe type C size template is N12, namely N11+ N12 equals N1, the number of the left foot templates of the B-shoe type D size is M21, the number of the right foot templates is N22, and N21+ N22 equals N2; the templates are sequentially arranged from No. 0 to SUM-1, the ith template is obtained in the matching process, if i +1 is less than or equal to M, the sole is judged to be of type A, and if not, the sole is judged to be of type B; if i +1 is less than or equal to M1 in the A type, the size of the sole is judged to be the size of C in the A type, otherwise the size of D in the A type is judged; if i +1 is not more than M11 in the A-class C-size sole template, the sole can be identified as a left sole of the A-class C-size sole, otherwise, the sole is a right sole of the A-class C-size sole. And matching the multiple templates according to the multilevel catalogue hierarchy, and finally accurately identifying the material information of the sole.
In addition, based on the above identification and positioning method based on matching of the backlight module and the multiple templates, an embodiment of the present invention provides an identification and positioning system based on matching of the backlight module and the multiple templates, including:
the image acquisition module is used for acquiring an image of the target area to obtain a sole image to be identified;
the image processing module is used for carrying out image smoothing processing on the sole image to be identified to obtain the template outline of the sole image to be identified, matching the template outline information of the sole image to be identified in a preset sole template base based on the template outline information of the sole image to be identified to obtain the sole information corresponding to the template outline information of the sole image to be identified, wherein,
the image acquisition module comprises an image acquisition module 10 and a backlight module, wherein the image acquisition module 10 is arranged at the top of the backlight module, the image acquisition module 10 is fixedly connected with the backlight module, the image acquisition module 10 is connected with the image processing module, the bottom of the backlight module is provided with a transmission module 20, a material induction module 30 and an illumination module 50, the illumination module 50 is arranged under the transmission module 20 and corresponds to the image acquisition module 10 in position, the material induction module 30 and the illumination module 50 are connected with the main control module, and the top of the backlight module is fixedly connected with the bottom of the backlight module.
The method and the device provided by the embodiment of the invention can be combined on a device for realization. Taking the device as an example, fig. 2-5 are schematic structural diagrams of an image capturing module according to an embodiment of the present invention.
In this embodiment, the image acquisition module includes an image acquisition module and a backlight module, the top of the image acquisition module is an image acquisition module 10, the backlight module is fixedly mounted on the machine table 60, the bottom of the backlight module is a base, the base is provided with a transmission module 20, a material sensing module 30 and an illumination module 50, the illumination module 50 is arranged under the transmission module 20 and corresponds to the position of the image acquisition module 10, and the material sensing module 30 and the illumination module 50 are connected with the main control module. Backlight unit top and base horizontal direction are through two aluminium alloy fixed connection, the corner is fixed with the right angle fixed plate, install the aluminium alloy about in the backlight unit, and be connected with backup pad 21, the fixed sliding connection of locking sleeve 22 is passed through to the aluminium alloy both sides, locking sleeve 22 inboard and rotatory driving shaft 23, rotatory driven shaft 24 is coaxial, make the rotation axis can 360 degrees free rotation, transportation module 20 is installed in the rotation axis outside, drive module 40 is installed as the drive shaft to rotatory driving shaft, it forwards to drive module 40 to drive down rotatory driving shaft 23, make transmission module 20 rotatory, the transmission material is from one end to the other end, both sides aluminium alloy top, it installs material response module 30 to be located image acquisition module 10 below position, through material response module receives material arrival signal.
In this embodiment, the illumination module 50 is a surface light source, and light provided by the surface light source is irradiated from bottom to top, so that the brightness in the backlight module meets the requirement of the image acquisition module 10 for image acquisition on the target area.
In this embodiment, the transportation module 20 is a transparent conveyor belt, and is used for conveying materials on the one hand, and on the other hand, the light provided by the surface light source can penetrate through the conveyor belt to provide a light source meeting the image acquisition requirement.
Specifically, the sole reaches the position of the material sensing module 30 from one end through the transportation module 20, the material sensing module 30 receives a sole arrival signal and sends the sole arrival signal to the central control module, the central control module sends a stop signal to the driving module 40 to control the conveyor belt to stop transmission on one hand, and sends an image acquisition signal to the image acquisition module 10 on the other hand; when the image acquisition module 10 receives an image acquisition signal, the light source controller is controlled through an IO signal, the image acquisition module 10 acquires an image of a target area while the illumination module 50 is switched on, and the illumination module 50 is powered off after a sole image to be identified is obtained.
In some embodiments, the image processing module locates the to-be-identified sole image, the weight is set to be 50-230 through binarization processing, when the grey value of a point pixel in the area is smaller than the set weight, the area where the material is located is determined to be a material area, the area where the material is located can be extracted, an area outline is formed by the edge-most pixel, the coordinate (xi, yi) of each pixel is obtained, and the barycentric coordinate of the area is obtained as:
The embodiment of the invention provides a recognition and positioning method and system based on matching of a backlight module and multiple templates, which are used for realizing rapid and accurate recognition and positioning of different types of products by utilizing a machine vision algorithm and matching with the backlight module and adopting a multi-template matching algorithm after the products are sent into the backlight module in the automatic production of the shoe manufacturing industry, and have the advantages of simple operation and low technical cost.
In addition, it should be noted that the specific embodiments described in the present specification may differ in the shape of the components, the names of the components, and the like. All equivalent or simple changes of the structure, the characteristics and the principle of the invention which are described in the patent conception of the invention are included in the protection scope of the patent of the invention. Various modifications, additions and substitutions for the specific embodiments described may be made by those skilled in the art without departing from the scope of the invention as defined in the accompanying claims.
Claims (10)
1. A recognition and positioning method based on backlight module and multi-template matching is characterized by comprising the following steps:
acquiring an image of a target area based on an image acquisition module to obtain a sole image to be identified;
carrying out image smoothing processing on the sole image to be identified through an image processing module to obtain template contour information of the sole image to be identified;
and matching the outline information of the sole image template to be identified in a preset sole template base based on the outline information of the sole image template to be identified to obtain sole information corresponding to the outline information of the sole image template to be identified.
2. The identification and location method based on backlight module and multi-template matching as claimed in claim 1, wherein the sole template library is provided with multi-level directories, wherein the first level directory is the sole shoe type, the second level directory is the sole size, the third level directory is the left and right foot, and the sole template library is updated and supplemented based on the historical sole information.
3. The method as claimed in claim 2, wherein the templates in each level of directory are traversed one by one and recorded in the template array.
4. The identification and location method based on the matching of the backlight module and the multiple templates as claimed in claim 3, wherein when the first-level template is matched, the matched shoe type template information is obtained from the template array, the corresponding first-level template serial number is obtained, the size template information of the corresponding shoe type is obtained through the second-level template matching, the corresponding second-level template serial number is obtained, finally, the left and right foot template information is obtained through the third-level template matching, the corresponding third-level template serial number is obtained, and the sole information is obtained based on the obtained third-level template serial number matching.
5. The identification and positioning method based on the backlight module and the multi-template matching as claimed in claim 1, wherein the image processing module performs iterative processing and Gaussian smoothing on the sole image to be identified, removes noise, and obtains template profile information of the sole image to be identified.
6. The identification and positioning method based on backlight module and multi-template matching as claimed in claim 1, wherein the image acquisition module comprises an image acquisition module and a backlight module, the image acquisition module is disposed at the top of the backlight module, the image acquisition module is fixedly connected with the backlight module, the image acquisition module is connected with the image processing module, the bottom of the backlight module is provided with a transmission module, a material sensing module and an illumination module, the illumination module is disposed under the transmission module and corresponds to the image acquisition module, the material sensing module and the illumination module are connected with the main control module, and the top of the backlight module is fixedly connected with the bottom of the backlight module.
7. The identification and positioning method based on backlight module and multi-template matching according to claim 6, wherein the image acquisition module comprises a camera, a camera support and a camera lens;
the camera bracket is fixedly arranged at the top of the backlight module;
the camera is arranged on the camera bracket;
the camera lens is connected to the camera.
8. The method as claimed in claim 6, wherein the illumination module is a surface light source.
9. The identification and location method based on backlight module and multi-template matching as claimed in claim 6, wherein the transportation module is a transparent conveyor belt.
10. The utility model provides an discernment and positioning system based on backlight unit and many templates match which characterized in that includes:
the image acquisition module is used for acquiring an image of the target area to obtain a sole image to be identified;
the image processing module is used for carrying out image smoothing processing on the sole image to be identified to obtain the template outline of the sole image to be identified, matching the template outline information of the sole image to be identified in a preset sole template base based on the template outline information of the sole image to be identified to obtain the sole information corresponding to the template outline information of the sole image to be identified, wherein,
the image acquisition module comprises an image acquisition module and a backlight module, the image acquisition module is arranged at the top of the backlight module, the image acquisition module is fixedly connected with the backlight module, the image acquisition module is connected with the image processing module, the bottom of the backlight module is provided with a transmission module, a material sensing module and a lighting module, the lighting module is arranged under the transmission module and corresponds to the position of the image acquisition module, the material sensing module and the lighting module are connected with the main control module, and the top of the backlight module is fixedly connected with the bottom of the backlight module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111135769.0A CN113837291A (en) | 2021-09-27 | 2021-09-27 | Identification and positioning method and system based on backlight module and multi-template matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111135769.0A CN113837291A (en) | 2021-09-27 | 2021-09-27 | Identification and positioning method and system based on backlight module and multi-template matching |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837291A true CN113837291A (en) | 2021-12-24 |
Family
ID=78970785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111135769.0A Pending CN113837291A (en) | 2021-09-27 | 2021-09-27 | Identification and positioning method and system based on backlight module and multi-template matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837291A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2003903728A0 (en) * | 2003-07-21 | 2003-07-31 | Hao Hang Zheng | Method and system for performing combined image classification storage and rapid retrieval on a computer database |
| FR2872317A1 (en) * | 2004-06-08 | 2005-12-30 | Do Labs Sa | METHOD FOR IMPROVING THE QUALITY OF USE OF A SERVICE RELATING TO AT LEAST ONE MULTIMEDIA DATA |
| WO2007000758A1 (en) * | 2005-06-27 | 2007-01-04 | Comodo Technologies Ltd. | Automated shoe fitting using shoe and adapter system |
| CN104424230A (en) * | 2013-08-26 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Network commodity recommendation method and device |
| US9430715B1 (en) * | 2015-05-01 | 2016-08-30 | Adobe Systems Incorporated | Identifying and modifying cast shadows in an image |
| WO2017193776A1 (en) * | 2016-05-12 | 2017-11-16 | 京东方科技集团股份有限公司 | Light apparatus and usage method thereof |
| US20190139200A1 (en) * | 2017-11-06 | 2019-05-09 | Canon Kabushiki Kaisha | Image processing apparatus, imaging apparatus, lens apparatus, image processing method, and recording medium |
| CN210374993U (en) * | 2019-09-17 | 2020-04-21 | 重庆庆图光电有限公司 | Injection molding size profile detection machine |
| CN112785164A (en) * | 2021-01-27 | 2021-05-11 | 中国电建集团华东勘测设计研究院有限公司 | Platform for digitally decomposing, managing and applying flood prevention and emergency rescue technical scheme |
| CN113255565A (en) * | 2021-06-11 | 2021-08-13 | 知守科技(杭州)有限公司 | Adaptive shoe type recognition method, device, system, electronic device and storage medium |
-
2021
- 2021-09-27 CN CN202111135769.0A patent/CN113837291A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2003903728A0 (en) * | 2003-07-21 | 2003-07-31 | Hao Hang Zheng | Method and system for performing combined image classification storage and rapid retrieval on a computer database |
| FR2872317A1 (en) * | 2004-06-08 | 2005-12-30 | Do Labs Sa | METHOD FOR IMPROVING THE QUALITY OF USE OF A SERVICE RELATING TO AT LEAST ONE MULTIMEDIA DATA |
| WO2007000758A1 (en) * | 2005-06-27 | 2007-01-04 | Comodo Technologies Ltd. | Automated shoe fitting using shoe and adapter system |
| CN104424230A (en) * | 2013-08-26 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Network commodity recommendation method and device |
| US9430715B1 (en) * | 2015-05-01 | 2016-08-30 | Adobe Systems Incorporated | Identifying and modifying cast shadows in an image |
| WO2017193776A1 (en) * | 2016-05-12 | 2017-11-16 | 京东方科技集团股份有限公司 | Light apparatus and usage method thereof |
| US20190139200A1 (en) * | 2017-11-06 | 2019-05-09 | Canon Kabushiki Kaisha | Image processing apparatus, imaging apparatus, lens apparatus, image processing method, and recording medium |
| CN210374993U (en) * | 2019-09-17 | 2020-04-21 | 重庆庆图光电有限公司 | Injection molding size profile detection machine |
| CN112785164A (en) * | 2021-01-27 | 2021-05-11 | 中国电建集团华东勘测设计研究院有限公司 | Platform for digitally decomposing, managing and applying flood prevention and emergency rescue technical scheme |
| CN113255565A (en) * | 2021-06-11 | 2021-08-13 | 知守科技(杭州)有限公司 | Adaptive shoe type recognition method, device, system, electronic device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 曾强: "基于HALCON的刹车片轮廓缺陷检测方法研究", 《煤矿机械》, no. 2016, 31 August 2016 (2016-08-31), pages 143 - 146 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4679073B2 (en) | Tire unevenness pattern inspection method and tire unevenness pattern inspection apparatus | |
| CN110941462B (en) | System and method for automatically learning product manipulation | |
| CN110675376A (en) | PCB defect detection method based on template matching | |
| KR20190060875A (en) | Automated identification of shoe parts | |
| JP7069736B2 (en) | Product information management programs, methods and equipment | |
| JP2013541779A (en) | Continuous charting of the severity of non-uniformity to detect web-based material variability | |
| CN114897864A (en) | Workpiece detection and defect judgment method based on digital-analog information | |
| CN110281240A (en) | The positioning of liquid crystal display panel glass, pick-up method and system and vision processing system | |
| CN115078392A (en) | Semiconductor chip defect detection equipment and method | |
| CN112258455A (en) | Detection method for detecting spatial position of part based on monocular vision | |
| CN114419437A (en) | Workpiece sorting system based on 2D vision and control method and control device thereof | |
| US9361695B2 (en) | Method of recognizing a position of a workpiece from a photographed image | |
| CN112284258B (en) | System for measuring cable structure size parameters based on machine vision algorithm | |
| CN108682014A (en) | Method for registering images, device, storage medium and image printing pipelining equipment | |
| CN109804730B (en) | Substrate inspection apparatus and substrate distortion compensation method using the same | |
| CN113837291A (en) | Identification and positioning method and system based on backlight module and multi-template matching | |
| CN117291918A (en) | Automobile stamping part defect detection method based on three-dimensional point cloud | |
| CN114693678A (en) | Intelligent detection method and device for workpiece quality | |
| JP2003202214A (en) | Shape measuring device and shape measuring method | |
| US20190302004A1 (en) | Adaptive Method for a Light Source | |
| CN106325611A (en) | Optical touch device and width detection method thereof | |
| CN108898585B (en) | Shaft part detection method and device | |
| JPH11175150A (en) | Stop position deviation amount detecting device for moving body | |
| CN111862196A (en) | Method, apparatus and computer-readable storage medium for detecting through-hole of flat object | |
| CN114693681B (en) | Zipper production defect intelligent detection method and system based on optical means |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |