CN106903075A - A kind of vamp logo multi-directional visions detection method and system - Google Patents
A kind of vamp logo multi-directional visions detection method and system Download PDFInfo
- Publication number
- CN106903075A CN106903075A CN201710282797.2A CN201710282797A CN106903075A CN 106903075 A CN106903075 A CN 106903075A CN 201710282797 A CN201710282797 A CN 201710282797A CN 106903075 A CN106903075 A CN 106903075A
- Authority
- CN
- China
- Prior art keywords
- shoes
- vamp
- module
- logo
- detection
- 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.)
- Withdrawn
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of vamp logo multi-directional visions detection method and system, method is shunted including (1) shoes;(2) IMAQ;(3) image detection classification;(4) shoes interflow;(5) sorting is sorted out.The detection of present invention computer vision replaces manual detection, greatly reduces labour cost and workload, can also be carried out without experienced person's detection, and objectivity is strong;In addition, two shoes are separated, every shoes individually use the multiple multi-faceted detection of CCD industrial cameras, it is ensured that the false drop rate and loss of shoes logo are relatively low.
Description
Technical field
The present invention relates to the technical field of shoes detection, more particularly to a kind of vamp logo multi-directional vision detection methods
And system.
Background technology
China is a footwear big trading nation, and annual footwear export volume accounts for 30% of total output or so, be footwear export volume most
Many countries, and growth trend year by year is presented.Used as Chinese tradition industry, the quality testing of shoes is always the pain of the sector
Point.The missing of logo and dislocation all can cause to have a strong impact on to the outward appearance of shoes and quality, hinder it to sell.For a long time, footwear
Class logo detections are general by being accomplished manually, and manual detection relies primarily on the experience of reviewer, and subjectivity is strong, causes evaluation criterion
It is inconsistent, flase drop and missing inspection are often produced, even if skilled reviewer can only also have found about 70% logo defects.Separately
Outward, footwear logo defects detections are a heavy manual labor, the eyesight of very big damage survey workman for workman.Cause
Footwear are carried out defects detection by this using vision instead of human eye, the inexorable trend as Chinese shoemaking development.
However, different from the defects detection of other industry, vamp logo distributions are more and irregular, if every to vamp respectively
Logo defects are individually detected at individual position, then workload is extremely huge, and hardware is difficult layout.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, there is provided a kind of labour cost is low, can substantially reduce work
Amount, objectivity are strong, false drop rate and the low vamp logo multi-directional vision detection methods of loss.
To achieve the above object, technical scheme provided by the present invention is:Method is comprised the following steps:
(1) shoes of left and right two of a pair of product shoes to be detected are branched to two different detection stations by diverter module;
The vamp image of shoes corresponding to image capture module Real-time Collection on (2) two detection stations;
Image processing module on (3) two detection stations carries out defects detection and classification to the vamp image for collecting,
Testing result generation is reported and stored;
(4) the shoes interflow that interflow module has detected separate two is together;
(5) sorting module sorts out simultaneously the product shoes of different logo defects according to the testing result of image processing module
Sort out.
Further, the image capture module in the step (2) on two detection stations is using multiple CCD industry phases
Machine corresponds to side toe-cap and heel, left and right sides vamp, upside upper of a shoe and vamp before and after shoes respectively, comprehensive so as to reach shoes
The purpose of defects detection.
Further, step (2) the vamp IMAQ is concretely comprised the following steps:Detection station is reached after shoes are shunted
When, photoelectric sensor is triggered, after servomotor receives signal, the LED light source that driving is fixed with CCD industrial cameras declines, and has treated
Complete covering selectively trigger each detecting position CCD industrial cameras after shoes and taken pictures.
Further, step (3) image procossing is comprised the following steps that:
1) masterplate is chosen:
A) color space conversion;
B the ROI region where) choosing all logo of vamp, generates template;
C) selected template is preserved to PC ATLs, as the standard form of subsequent match;
2) stencil matching:
A) color space conversion;
B) the similarity degree of measurement subregion and To Template;
C) Optimizing Search strategy;
D calculating speed) is improved.
Further, the masterplate is chosen and is following steps with the color space conversion in stencil matching:
Image is transformed into hsv color space formula from RGB color is:
V=max
Wherein, (r, g, b) is respectively a red, green, blue coordinate for color, and between (0,1), max is the value of r, g, b
Maximum in r, g, b, min is r, g, and the minimum value in b, [0,360 °] of h ∈ are the hue angle of angle, and s, l ∈ [0,1] are full
With degree and brightness.
Further, step (3) the stencil matching vacuum metrics subregion and To Template similarity degree are calculated as follows:
Template T (m × n pixel) is overlayed into searched figure S (W × H pixel) upper and lower translation, template covering search graph
Subgraph region Sij, wherein, i, j are subgraph SijCoordinate of the upper left corner on search graph S;By comparing the similitude of T and S, degree
Quantum region and the similarity degree of To Template.
Further, Optimizing Search strategy is specific as follows in step (3) template matches:According to measurement subregion and mesh
The coefficient correlation that mark template similarity degree is obtained, in search, if the coefficient correlation of current location is less than certain threshold value or is somebody's turn to do
Position is far from the target's center of previous frame, and the step-length of search will be increased, otherwise then reduce step-size in search.
Further, calculating speed is improved in step (3) template matches specific as follows:Take error threshold E0, work as E
(i, j) > E0When, stop the calculating of the point, continue subsequent point and calculate, so as to obtain desired result;The error calculation formula
It is as follows:Wherein, masterplate T has m × n pixel, SijFor template is covered
The subgraph region of lid search graph, i, j are subgraph SijCoordinate of the upper left corner on search graph S.
To achieve the above object, the present invention additionally provides one kind for realizing above-mentioned vamp logo multi-directional visions detection side
The system of method, system includes diverter module, image capture module, image processing module, interflow module and sorting module;
The shoes of left and right two of a pair of product shoes to be detected are branched to two different detection stations by diverter module;
Image capture module, the vamp image of corresponding shoes on two detection stations of Real-time Collection;
Image processing module, the vamp image to being collected on two detection stations carries out defects detection and classification, and will
Testing result generation report;
Interflow module, the shoes interflow that separate two have been detected is together;
The product shoes of different logo defects are sorted out and returned by sorting module, the testing result according to image processing module
Class;
Wherein, described image processing module includes software interface display module, image processing algorithm unit and database list
Unit;
Software interface display module, for man-machine interaction and finally by the position of shoes logo defects and type generation detection
Report;
Image processing algorithm unit, defects detection and classification are carried out by algorithm to the vamp image for collecting;
Database Unit, stores the examining report on shoes logo defective locations and type.
Further, described image acquisition module include LED light source, multiple CCD industrial cameras, Z axis servo module and
Servomotor;Wherein, LED light source is spherical semiclosed case, and bottom opens, and light source side wall is provided with multiple for fixing CCD industry
The fixing hole of camera, corresponds to multiple detecting positions of product shoes respectively;The Z axis servo module is connected with LED light source, is placed in Z axis
Servomotor above servo module drives the Z axis servo module to drive LED light source to realize vertical direction elevating movement.
Compared with prior art, this programme principle and advantage is as follows:
Detected with computer vision and replace manual detection, labour cost and workload are greatly reduced, without experienced
Personnel's detection can also be carried out, and objectivity is strong;In addition, two shoes are separated, every shoes individually use multiple CCD industrial cameras
Multi-faceted detection, it is ensured that the false drop rate and loss of shoes logo are relatively low.
Brief description of the drawings
Fig. 1 is a kind of structural representation of vamp logo multi-directional vision detecting systems of the embodiment of the present invention;
Fig. 2 is the structure of image capture module in a kind of vamp logo multi-directional vision detecting systems of the embodiment of the present invention
Figure;
Fig. 3 is a kind of workflow diagram of vamp logo multi-directional vision detection methods of the embodiment of the present invention;
Fig. 4 is the image processing algorithm flow in a kind of vamp logo multi-directional vision detection methods of the embodiment of the present invention
Figure.
Specific embodiment
With reference to specific embodiment, the invention will be further described:
Referring to shown in accompanying drawing 1-2, a kind of vamp logo multi-directional vision detecting systems described in the present embodiment, including shunting
Module 1, image capture module 2, image processing module 3, interflow module 4 and sorting module 5.Wherein,
Image capture module 2 includes 9, five CCD industrial cameras 10 of LED light source, Z axis servo module 11 and servomotor
12;LED light source 9 is spherical semiclosed case, and bottom opens, and light source side wall is provided with five for fixing consolidating for CCD industrial cameras 10
Determine hole, five detecting positions of product shoes are corresponded to respectively;Z axis servo module 11 is connected with LED light source 9, is placed in Z axis servo module 11
The servomotor 12 of top drives the Z axis servo module 11 to drive LED light source 9 to realize vertical direction elevating movement.
Image processing module 3 includes software interface display module 6, image processing algorithm unit 7 and Database Unit 8.
Workflow is as shown in Figure 3-4, specific as follows:
(1) left and right two shoes a, b of a pair of product shoes to be detected are branched to two different detection works by diverter module 1
Position;
The vamp image of shoes corresponding to the Real-time Collection of image capture module 2 on (2) two detection stations:
When detection station is reached after shoes a, b shunting, triggering photoelectric sensor (without display in figure), servomotor 12
After receiving signal, decline the LED light source 9 for being fixed with CCD industrial cameras 10, each is selectively triggered after shoes are covered completely
Detecting position CCD industrial cameras 10 are taken pictures;Five CCD industrial cameras 10 (CCD1, CCD2, CCD3, CCD4, CCD5) are right respectively
Side toe-cap and heel, left and right sides vamp, upside upper of a shoe and vamp before and after shoes are answered, so as to reach the comprehensive defects detection of shoes
Purpose (a CCD industrial camera of shoes b sides is blocked due to angle);After the completion of taking pictures, servomotor 12 drives Z axis
Servo module 11 drives LED light source 9 to rise;
The vamp image that image processing module 3 pairs on (3) two detection stations is collected carries out defects detection and classification,
Testing result generation is reported and stored;Comprise the following steps that:
First passing through software interface display module 6 carries out man-machine interaction, then carries out defect inspection by image processing algorithm unit 7
Survey, image detection is comprised the following steps that:
1) masterplate is chosen:
A) color space conversion:
Image is transformed into hsv color space formula from RGB color is:
V=max
Wherein, (r, g, b) is respectively a red, green, blue coordinate for color, and between (0,1), max is the value of r, g, b
Maximum in r, g, b, min is r, g, and the minimum value in b, [0,360 °] of h ∈ are the hue angle of angle, and s, l ∈ [0,1] are full
With degree and brightness;
B the ROI region where) choosing all logo of vamp, generates template, and the ratio that logo accounts for ROI region is 40%;
C) selected template is preserved to PC ATLs, as the standard form of subsequent match:
In initialization procedure, after template is chosen, PC model libraries are saved to, as the standard form of subsequent match;Just
The template of beginningization is chosen and is only carried out once, and follow-up logo detections need not be chosen again;
2) stencil matching:
A) color space conversion, the color space conversion step during the switch process is chosen with masterplate is consistent;
B) the similarity degree of measurement subregion and To Template:
Stencil matching vacuum metrics subregion and To Template similarity degree are calculated as follows:
Template T (m × n pixel) is overlayed into searched figure S (W × H pixel) upper and lower translation, template covering search graph
Subgraph region Sij, wherein, i, j are subgraph SijCoordinate of the upper left corner on search graph S;By comparing the similitude of T and S, degree
Quantum region and the similarity degree of To Template;
C) Optimizing Search strategy:
According to the coefficient correlation that measurement subregion and To Template similarity degree are obtained, in search, if current location
Coefficient correlation is far from the target's center of previous frame less than certain threshold value or the position, and the step-length of search will be increased, otherwise then
Reduce step-size in search;
D calculating speed) is improved:
Take error threshold E0, as E (i, j) > E0When, stop the calculating of the point, continue subsequent point and calculate, so as to be wanted
Result;The error calculation formula is as follows:Wherein, masterplate T has
M × n pixel, SijThe subgraph region of search graph, i are covered for template, j is subgraph SijCoordinate of the upper left corner on search graph S;
Database Unit 8 stores the examining report of shoes logo defective locations and type.
(4) shoes that interflow module 4 has detected separate two after detection classification collaborate together;
(5) sorting module 5 sorts out the product shoes of different logo defects according to the testing result of image processing module
And sort out.
The detection of the present embodiment computer vision replaces manual detection, labour cost and workload is substantially reduced, without having
Personnel's detection of experience can also be carried out, and objectivity is strong;In addition, two shoes are separated, every shoes individually use multiple CCD works
The multi-faceted detection of industry camera, it is ensured that the false drop rate and loss of shoes logo are relatively low.
The examples of implementation of the above are only the preferred embodiments of the invention, not limit implementation model of the invention with this
Enclose, therefore the change that all shapes according to the present invention, principle are made, all should cover within the scope of the present invention.
Claims (10)
1. a kind of vamp logo multi-directional vision detection methods, it is characterised in that:Comprise the following steps:
(1) shoes of left and right two of a pair of product shoes to be detected are branched to two different detection stations by diverter module;
The vamp image of shoes corresponding to image capture module Real-time Collection on (2) two detection stations;
Image processing module on (3) two detection stations carries out defects detection and classification to the vamp image for collecting, and will examine
Result generation is surveyed to report and store;
(4) the shoes interflow that interflow module has detected separate two is together;
(5) product shoes of different logo defects are sorted out and returned by sorting module according to the testing result of image processing module
Class.
2. a kind of vamp logo multi-directional vision detection methods according to claim 1, it is characterised in that:The step
(2) image capture module on two detection stations corresponds to side toe-cap before and after shoes respectively using multiple CCD industrial cameras
With heel, left and right sides vamp, upside upper of a shoe and vamp, so as to reach the purpose of the comprehensive defects detection of shoes.
3. a kind of vamp logo multi-directional vision detection methods according to claim 1, it is characterised in that:The step
(2) vamp IMAQ is concretely comprised the following steps:When detection station is reached after shoes shunting, photoelectric sensor, servo electricity are triggered
After machine receives signal, the LED light source that driving is fixed with CCD industrial cameras declines, and selectively triggers each after shoes are covered completely
Individual detecting position CCD industrial cameras are taken pictures.
4. a kind of vamp logo multi-directional vision detection methods according to claim 1, it is characterised in that:The step
(3) image procossing is comprised the following steps that:
1) masterplate is chosen:
A) color space conversion;
B the ROI region where) choosing all logo of vamp, generates template;
C) selected template is preserved to PC ATLs, as the standard form of subsequent match;
2) stencil matching:
A) color space conversion;
B) the similarity degree of measurement subregion and To Template;
C) Optimizing Search strategy;
D calculating speed) is improved.
5. a kind of vamp logo multi-directional vision detection methods according to claim 4, it is characterised in that:The masterplate choosing
Take and be following steps with the color space conversion in stencil matching:
Image is transformed into hsv color space formula from RGB color is:
V=max
Wherein, (r, g, b) is respectively a red, green, blue coordinate for color, and between (0,1), max is r, g to the value of r, g, b,
Maximum in b, min is r, g, and the minimum value in b, [0,360 °] of h ∈ are the hue angle of angle, and s, l ∈ [0,1] are saturation degree
And brightness.
6. a kind of vamp logo multi-directional vision detection methods according to claim 4, it is characterised in that:The step
(3) stencil matching vacuum metrics subregion and To Template similarity degree are calculated as follows:
Template T (m × n pixel) is overlayed into searched figure S (W × H pixel) upper and lower translation, template covers the son of search graph
Graph region Sij, wherein, i, j are subgraph SijCoordinate of the upper left corner on search graph S;By comparing the similitude of T and S, measurement
Region and the similarity degree of To Template.
7. a kind of vamp logo multi-directional vision detection methods according to claim 4, it is characterised in that:The step
(3) Optimizing Search strategy is specific as follows in template matches:It is related to what To Template similarity degree was obtained according to measurement subregion
Coefficient, in search, if the coefficient correlation of current location less than certain threshold value or the position from previous frame target's center very
Far, the step-length of search will be increased, otherwise then reduce step-size in search.
8. a kind of vamp logo multi-directional vision detection methods according to claim 4, it is characterised in that:Step (3) mould
It is specific as follows calculating speed to be improved in plate matching:Take error threshold E0, as E (i, j) > E0When, stop the calculating of the point, continue next
Point is calculated, so as to obtain desired result;The error calculation formula is as follows:
Wherein, masterplate T has m × n pixel, SijThe subgraph region of search graph, i are covered for template, j is subgraph SijThe upper left corner is being searched
Coordinate on rope figure S.
9. a kind of system for realizing vamp logo multi-directional vision detection methods described in claim 1, it is characterised in that:Bag
Include diverter module (1), image capture module (2), image processing module (3), interflow module (4) and sorting module (5);
The shoes of left and right two of a pair of product shoes to be detected are branched to two different detection stations by diverter module (1);
Image capture module (2), the vamp image of corresponding shoes on two detection stations of Real-time Collection;
Image processing module (3), the vamp image to being collected on two detection stations carries out defects detection and classification, and will inspection
Survey result generation report;
Interflow module (4), the shoes interflow that separate two have been detected is together;
The product shoes of different logo defects are sorted out and returned by sorting module (5), the testing result according to image processing module
Class;
Wherein, described image processing module (3) includes software interface display module (6), image processing algorithm unit (7) and data
Library unit (8);
Software interface display module (6), for man-machine interaction and finally by the position of shoes logo defects and type generation detection
Report;
Image processing algorithm unit (7), defects detection and classification are carried out by algorithm to the vamp image for collecting;
Database Unit (8), stores the examining report on shoes logo defective locations and type.
10. a kind of vamp logo multi-directional vision detecting systems according to claim 9, it is characterised in that:Described image
Acquisition module (2) includes LED light source (9), multiple CCD industrial cameras (10), Z axis servo module (11) and servomotor
(12);Wherein, LED light source (9) is spherical semiclosed case, and bottom opens, and light source side wall is provided with multiple for fixing CCD industry phases
The fixing hole of machine (10), corresponds to multiple detecting positions of product shoes respectively;The Z axis servo module (11) is with LED light source (9) even
Connect, the servomotor (12) being placed in above Z axis servo module (11) drives Z axis servo module (11) to drive LED light source (9) real
Existing vertical direction elevating movement.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710282797.2A CN106903075A (en) | 2017-04-26 | 2017-04-26 | A kind of vamp logo multi-directional visions detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710282797.2A CN106903075A (en) | 2017-04-26 | 2017-04-26 | A kind of vamp logo multi-directional visions detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106903075A true CN106903075A (en) | 2017-06-30 |
Family
ID=59211139
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710282797.2A Withdrawn CN106903075A (en) | 2017-04-26 | 2017-04-26 | A kind of vamp logo multi-directional visions detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106903075A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107677682A (en) * | 2017-11-07 | 2018-02-09 | 泉州创力模具有限公司 | A kind of footwear mould surface damage detection device and detection method |
CN108816810A (en) * | 2018-07-03 | 2018-11-16 | 青岛永悦光迅技术有限责任公司 | A kind of express delivery security check passage, rays safety detection apparatus and system |
CN109839381A (en) * | 2017-11-28 | 2019-06-04 | 宝成工业股份有限公司 | The vision inspection apparatus of shoes part |
CN116952303A (en) * | 2023-07-27 | 2023-10-27 | 浙江卓诗尼鞋业有限公司 | Comprehensive detection equipment for multiple functions of shoes |
CN117517314A (en) * | 2024-01-04 | 2024-02-06 | 歌尔股份有限公司 | Visual inspection apparatus |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07185474A (en) * | 1993-12-24 | 1995-07-25 | Sandvik Kk | Classifying apparatus |
JPH10236642A (en) * | 1997-02-24 | 1998-09-08 | Maki Seisakusho:Kk | Feed-merging device for pans on which agricultural products are placed |
JP2001019152A (en) * | 1999-07-06 | 2001-01-23 | Maki Mfg Co Ltd | Joining device for conveyed articles |
CN101027236A (en) * | 2004-06-21 | 2007-08-29 | 西门子共同研究公司 | High-rate space efficient article singulator |
CN101308607A (en) * | 2008-06-25 | 2008-11-19 | 河海大学 | Moving target tracking method by multiple features integration under traffic environment based on video |
WO2009110066A1 (en) * | 2008-03-04 | 2009-09-11 | ヤンマー株式会社 | Goods carrier machine |
CN101639858A (en) * | 2009-08-21 | 2010-02-03 | 深圳创维数字技术股份有限公司 | Image search method based on target area matching |
CN202710486U (en) * | 2012-07-20 | 2013-01-30 | 朱飞虎 | Automatic detection device of metal self-adhesive label |
CN103328119A (en) * | 2011-02-02 | 2013-09-25 | 莱特拉姆有限责任公司 | System and method for grading articles and selectively mixing graded articles |
CN105224945A (en) * | 2015-09-18 | 2016-01-06 | 电子科技大学 | A kind of automobile logo identification method based on joint-detection and identification algorithm |
CN205787337U (en) * | 2016-05-25 | 2016-12-07 | 深圳市华显光学仪器有限公司 | Diffuse-reflectance videomicroscopy |
CN106429364A (en) * | 2016-07-12 | 2017-02-22 | 广东丽柏特科技有限公司 | Sanitary ceramic semifinished product detection line |
CN206925022U (en) * | 2017-04-26 | 2018-01-26 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of vamp logo multi-directional vision detecting systems |
-
2017
- 2017-04-26 CN CN201710282797.2A patent/CN106903075A/en not_active Withdrawn
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07185474A (en) * | 1993-12-24 | 1995-07-25 | Sandvik Kk | Classifying apparatus |
JPH10236642A (en) * | 1997-02-24 | 1998-09-08 | Maki Seisakusho:Kk | Feed-merging device for pans on which agricultural products are placed |
JP2001019152A (en) * | 1999-07-06 | 2001-01-23 | Maki Mfg Co Ltd | Joining device for conveyed articles |
CN101027236A (en) * | 2004-06-21 | 2007-08-29 | 西门子共同研究公司 | High-rate space efficient article singulator |
WO2009110066A1 (en) * | 2008-03-04 | 2009-09-11 | ヤンマー株式会社 | Goods carrier machine |
CN101308607A (en) * | 2008-06-25 | 2008-11-19 | 河海大学 | Moving target tracking method by multiple features integration under traffic environment based on video |
CN101639858A (en) * | 2009-08-21 | 2010-02-03 | 深圳创维数字技术股份有限公司 | Image search method based on target area matching |
CN103328119A (en) * | 2011-02-02 | 2013-09-25 | 莱特拉姆有限责任公司 | System and method for grading articles and selectively mixing graded articles |
CN202710486U (en) * | 2012-07-20 | 2013-01-30 | 朱飞虎 | Automatic detection device of metal self-adhesive label |
CN105224945A (en) * | 2015-09-18 | 2016-01-06 | 电子科技大学 | A kind of automobile logo identification method based on joint-detection and identification algorithm |
CN205787337U (en) * | 2016-05-25 | 2016-12-07 | 深圳市华显光学仪器有限公司 | Diffuse-reflectance videomicroscopy |
CN106429364A (en) * | 2016-07-12 | 2017-02-22 | 广东丽柏特科技有限公司 | Sanitary ceramic semifinished product detection line |
CN206925022U (en) * | 2017-04-26 | 2018-01-26 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of vamp logo multi-directional vision detecting systems |
Non-Patent Citations (3)
Title |
---|
张浩等: "图像识别技术在电力设备监测中的应用", 《电力系统保护与控制》 * |
石美红等: "从RGB到HSV色彩空间转换公式的修正", 《纺织高校基础科学学报》 * |
胡焯源等: "基于HSV颜色空间的车身颜色识别算法", 《辽宁工业大学学报(自然科学版)》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107677682A (en) * | 2017-11-07 | 2018-02-09 | 泉州创力模具有限公司 | A kind of footwear mould surface damage detection device and detection method |
CN107677682B (en) * | 2017-11-07 | 2024-03-08 | 泉州创力模具有限公司 | Shoe mold surface damage detection device and detection method |
CN109839381A (en) * | 2017-11-28 | 2019-06-04 | 宝成工业股份有限公司 | The vision inspection apparatus of shoes part |
CN108816810A (en) * | 2018-07-03 | 2018-11-16 | 青岛永悦光迅技术有限责任公司 | A kind of express delivery security check passage, rays safety detection apparatus and system |
CN116952303A (en) * | 2023-07-27 | 2023-10-27 | 浙江卓诗尼鞋业有限公司 | Comprehensive detection equipment for multiple functions of shoes |
CN116952303B (en) * | 2023-07-27 | 2024-04-30 | 浙江卓诗尼鞋业有限公司 | Comprehensive detection equipment for multiple functions of shoes |
CN117517314A (en) * | 2024-01-04 | 2024-02-06 | 歌尔股份有限公司 | Visual inspection apparatus |
CN117517314B (en) * | 2024-01-04 | 2024-04-30 | 歌尔股份有限公司 | Visual inspection apparatus |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106903075A (en) | A kind of vamp logo multi-directional visions detection method and system | |
CN111445368B (en) | Garbage classification method, device and equipment based on machine vision and deep learning | |
CN101477631B (en) | Method, equipment for extracting target from image and human-machine interaction system | |
CN106238342A (en) | The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof | |
CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
CN105701476A (en) | Machine vision-based automatic identification system and method for production line products | |
CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
CN110570422B (en) | Capsule defect visual detection method based on matrix analysis | |
CN107301634A (en) | A kind of robot automatic sorting method and system | |
CN115908432A (en) | Material output quality detection system and prediction method | |
CN114881987B (en) | Hot-pressing light guide plate defect visual detection method based on improvement YOLOv5 | |
CN206925022U (en) | A kind of vamp logo multi-directional vision detecting systems | |
CN107016699A (en) | A kind of color coding approach of the variegated particle of automatic identification | |
CN106934425B (en) | A kind of industrial products counting method based on deep learning | |
CN113145473A (en) | Intelligent fruit sorting system and method | |
CN113319013A (en) | Apple intelligent sorting method based on machine vision | |
CN111369497B (en) | Walking type tree fruit continuous counting method and device | |
CN113240798A (en) | Intelligent material integrity detection and configuration method based on digital twinning and AR | |
CN206139529U (en) | Transparent roller bearing mechanism | |
CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
CN210377552U (en) | Fruit is multiaspect image acquisition device for classification | |
CN117079125A (en) | Kiwi fruit pollination flower identification method based on improved YOLOv5 | |
CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
CN116106319A (en) | Automatic detection method and system for defects of synthetic leather | |
CN115254655A (en) | Multi-index passion fruit quality grading method based on machine vision |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170630 |
|
WW01 | Invention patent application withdrawn after publication |