CN103033266A - Automatic detection device and method of plane figure color shading - Google Patents
Automatic detection device and method of plane figure color shading Download PDFInfo
- Publication number
- CN103033266A CN103033266A CN2012105294712A CN201210529471A CN103033266A CN 103033266 A CN103033266 A CN 103033266A CN 2012105294712 A CN2012105294712 A CN 2012105294712A CN 201210529471 A CN201210529471 A CN 201210529471A CN 103033266 A CN103033266 A CN 103033266A
- Authority
- CN
- China
- Prior art keywords
- classification
- value range
- permissible error
- time
- image
- 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
Images
Abstract
The invention relates to an automatic detection device of plane figure color shading based on machine vision technology. The automatic detection device of the plane figure color shading comprises a camera, a memorizer, a displayer and a processor. The camera shoots a plurality of plane figures on work pieces. The processor stores images shot by the camera in the memorizer. The processor establishes a first classification and a comparison standard. A deviation value is obtained by comparing an image shot for the K+1th time with the comparison standard. The deviation value is judged whether exceeding an allowed error range value or not. When the deviation value is in the allowed error range value, the image shot for the K+1 time are classified as the first classification. When the deviation value is beyond the allowed error range value, a second classification and a comparison standard are established. The displayer displays each classification result obtained. The automatic detection device of the plane figure color shading based on the machine vision technology can automatically detect the color shading and classify the color shading. The invention further relates to an automatic detection method of the plane figure color shading.
Description
Technical field
The present invention relates to a kind of planar graph aberration automatic detection device and method based on machine vision technique.
Background technology
Along with the raising of people's living standard, furniture, hotel finishing equipment is more and more diversified, and such as being made by materials such as pottery, plastics, timber, the kind of pattern color also gets more and more.For example, along with color, decorative pattern, the pattern of ceramic tile are more and more, the ceramic tile surface quality becomes increasingly complex.
At present, each quarry-tile factory leans on and manually according to the degree of aberration ceramic tile is carried out packet numbering, but human eye is because tired easily, and be subject to many factors and disturb (such as light, the state of mind etc.), misjudgement and erroneous judgement occur easily, thereby the inaccurate situation of color separation occurs, and production efficiency is low.
Summary of the invention
For the deficiencies in the prior art, purpose of the present invention is intended to provide a kind of planar graph aberration automatic detection device and method based on machine vision technique, and it can detect aberration and the automatic classification grouping of workpiece automatically.
For achieving the above object, the present invention adopts following technical scheme:
A kind of planar graph aberration automatic detection device, the processor that it comprises video camera, storer, display and is preset with the permissible error value range;
This video camera is used for taking the planar graph on some workpiece;
Processor is stored in storer with the image of shot by camera;
This display is used for each drawn classification results of video-stream processor.
Its thinking is:
1. after obtaining certain product great amount of images sample, according to product aberration allowed band all samples are divided into several classes, the contrast standard of class is the central value of category feature.
2. for new product, when obtaining one by one the product image, take the first width of cloth image as contrast standard.When image and certain class error of new acquisition just is integrated into such within allowed band.When such sample when generally getting 50-100 for fixed number M() in time calculate the feature mean values of such available sample as the adaptive updates value of such comparison standard.
3. when sample surpasses the permissible error scope of current all categories, found in addition new classification.
Its process is:
Processor is set up the first classification and with the image taken for the 1st time comparison standard as the first classification; The image of taking for the K+1 time compared with the first standard of comparing of classifying draw deviate; Deviate and permissible error value range are compared, and whether the judgment bias value exceeds the permissible error value range; When deviate is in the permissible error value range, with graphic collection to the first classification of the K+1 time shooting; When deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying, wherein K is positive integer;
After processor is set up the second classification, again the image of taking for the K+2 time is compared respectively with the first classification and the second standard of comparing of classifying, obtain respectively two deviates and also contrast and draw minimum deviation value; Minimum deviation value and permissible error value range are compared, judge whether minimum deviation value exceeds the permissible error value range; If minimum deviation value is in the permissible error value range, then the image with the K+2 time shooting is integrated in classification corresponding to minimum deflection; If minimum deviation value surpasses the permissible error value range, then set up the 3rd classification and with the image taken for the K+2 time as the 3rd comparison standard of classifying.
Before image is set up classification and comparison, processor will be stored in the characteristic index of comparing after the image digitazation of storer and calculate, wherein compare characteristic index calculating and comprise tone, brightness and saturation degree etc., the comparison characteristic index corresponding to image of the 1st time, the K+1 time and the K+2 time shooting that the classification comparison standard of the first to the 3rd classification is respectively video camera.
This planar graph aberration automatic detection device also comprises light-source box, photographic light sources, photoelectric sensor, travelling belt and is used for driving the conveyor drive of travelling belt;
Some workpiece are intervally arranged on travelling belt; Light-source box is the box body of an opening, and light-source box is located at travelling belt top, and the one side that light-source box has an opening faces travelling belt, and video camera is installed in the top in the light-source box, and photographic light sources is located in the photographic light sources case;
This photoelectric sensor is used for the detecting workpiece and enters light-source box and generate corresponding induced signal, and processor is taken the workpiece that enters in the light-source box according to the actuated signal control video camera that photoelectric sensor generates.
This photographic light sources is the LED fluorescent light, and this LED fluorescent light is by DC power supply.Consist of the flicker free light source.
This light-source box consists of by flat board and light shield are installed, and video camera and LED fluorescent light are installed on this installation flat board, and this installation is dull and stereotyped to become 30 degree to 60 degree angles with the end face of workpiece, scribble black coating or lining in this light shield to deceive Velveting.
Planar graph aberration automatic detection device also comprises the printer that is connected with processor.
A kind of planar graph aberration automatic testing method, it may further comprise the steps:
At the default aberration permissible error value range of processor;
Take planar graph on some workpiece by video camera;
The image of shot by camera is stored in storer;
Set up the first classification and with the image taken for the 1st time comparison standard as the first classification by processor;
By processor the image of taking for the K+1 time is compared with the first standard of comparing of classifying and to draw deviate;
By processor deviate and permissible error value range are compared, whether the judgment bias value exceeds the permissible error value range;
When deviate is in the permissible error value range, with graphic collection to the first classification of the K+1 time shooting;
When deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying;
Show each classification results by display;
Wherein K is positive integer.
Step " when deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying " further comprising the steps of afterwards:
The image of the K+2 time shooting and the standard of comparing of the first classification and the second classification are compared respectively, obtain respectively two deviates and contrast drawing minimum deviation value;
By processor minimum deviation value and permissible error value range are compared, judge whether minimum deviation value exceeds the permissible error value range;
If minimum deviation value in the permissible error value range, then with the graphic collection taken for the K+2 time in classification corresponding to minimum deflection;
If minimum deviation value surpasses the permissible error value range, then set up the 3rd classification and with the image taken for the K+2 time as the 3rd comparison standard of classifying.
Before image being set up classification and comparison, also comprise step " will be stored in the characteristic index of comparing after the image digitazation of storer calculates by processor ", wherein compare characteristic index calculating and comprise tone, brightness and saturation degree etc., the comparison characteristic index corresponding to image of the 1st time, the K+1 time and the K+2 time shooting that the classification comparison standard of the first to the 3rd classification is respectively video camera.
Beneficial effect of the present invention is as follows:
Above-mentioned planar graph aberration automatic detection device automatically snaps the planar graph of each workpiece, and according to default permissible error value range, planar array type digitizing, image blurring analysis and comparison with the grouping of classifying of each planar graph, and classification results is shown in display or directly prints, very directly perceived efficient.In addition, foregoing invention realizes the workpiece automatic transport and takes the location by photoelectric sensor, conveyor drive and travelling belt, also blocks the environment veiling glare by light-source box, detects to avoid the light disturbance aberration, thereby improves the accuracy that aberration detects.
Description of drawings
Fig. 1 is the system block diagram of the preferred embodiments of planar graph aberration automatic detection device of the present invention.
Fig. 2 is the structural representation of the planar graph aberration automatic detection device of Fig. 1.
Fig. 3 is the structure cut-open view synoptic diagram of light-source box of the planar graph aberration automatic detection device of Fig. 1.
Fig. 4 is the process flow diagram of the preferred embodiments of planar graph aberration automatic testing method of the present invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment, the present invention is described further:
See also Fig. 1 to 3, the present invention relates to a kind of planar graph aberration automatic detection device, for detection of the aberration of workpiece planarization figure, its preferred embodiments comprises processor 20, video camera 10, photoelectric sensor 60, conveyor drive 50, travelling belt 40, photographic light sources 92, storer 80, display 85, printer 30 and light-source box 98.The below is to describe as example the detection of the planar graph of ceramic tile 95.
This light-source box 98 is the box body of an opening, light-source box 98 is located at travelling belt 40 tops, and the one side that light-source box 98 has opening faces travelling belt 40, video camera 10 is installed in the top in the light-source box 98, photographic light sources 92 is located in the photographic light sources case 92, and photographic light sources 92 is installed on the sidewall of photographic light sources case.
This light-source box 98 is used for blocking the surrounding enviroment veiling glare, the light that this photographic light sources 92 sends possesses stablizes constant light intensity and photochromic coloured silk, so, can be so that the brightness of the taken picture of video camera 10 be subjected to the impact of environment veiling glare, thereby can reflect exactly the actual aberration of the planar graph of ceramic tile 95, be conducive to improve the accuracy of detection.In the present embodiment, this photographic light sources 92 adopts the LED fluorescent light of flicker free, and it is by DC power supply, and the operating voltage capable of regulating of LED fluorescent light, so that the workpiece uniform-illumination carries out high-speed capture thereby be beneficial to video camera 10.
This light-source box 98 consists of by flat board 982 and light shield 985 are installed, video camera 10 and LED fluorescent light are installed in this installation dull and stereotyped 982, this installation dull and stereotyped 982 becomes 30 degree to spend angles to 60 with the end face of workpiece, take the photograph to get complete workpiece picture to guarantee video camera 10, do not receive the specular light of workpiece, only receive diffuse reflection, to guarantee to obtain accurately surface of the work image.Scribble black coating or lining in this light shield 985 with black Velveting.
This photoelectric sensor 60 is located at light-source box 98 belows, is used for detecting ceramic tile 95 and enters light-source box 98 and generate corresponding induced signal.The ceramic tile 95 that 10 pairs in the actuated signal control video camera that processor 20 generates according to photoelectric sensor 60 enters in the light-source box 98 is taken, and again video camera 10 captured images is stored in storer 80.
The present invention sets up M classification (M is positive integer) automatically, and for convenience of description, the below is categorized as example and is described automatically to set up three:
For example, when the deviate of the image of relative the 1st shooting of image of taking for the 2nd time surpasses the permissible error value range, then set up Equations of The Second Kind and with the image taken for the 2nd time comparison standard as Equations of The Second Kind, again the comparison standard of the first kind and Equations of The Second Kind is compared with the image of the 3rd shooting respectively, draw respectively two deviates and obtain both relative minimum deviation value, if minimum deviation value is in the permissible error value range, then with the graphic collection taken for the 3rd time in classification corresponding to minimum deviation value, if minimum deviation value surpasses the permissible error value range, then set up the 3rd classification and with the image taken for the 3rd time comparison standard as the 3rd classification.
See also Fig. 4, the invention still further relates to a kind of planar graph aberration automatic testing method, its preferred embodiments may further comprise the steps:
Step S00: at processor 20 default aberration permissible error value range and classification numbers.
Step S01: by 10 planar graphs of taking on some workpiece of making a video recording.
Step S02: video camera 10 captured images are stored in storer 80.
Step S03: set up the first classification and with the image taken for the 1st time comparison standard as the first classification by processor 20.
Step S04: by processor 20 image of taking for the K+1 time being compared with the first standard of comparing of classifying draws deviate.
Step S05: by processor 20 deviate and permissible error value range are compared, whether the judgment bias value exceeds the permissible error value range.
Step S06: if deviate in the permissible error value range time, with graphic collection to the first classification of taking for the K+1 time.
Step S07: if when deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying.
Step S08: by processor 20 image of the K+2 time shooting and the standard of comparing of the first classification and the second classification are compared respectively, obtain respectively two deviates and contrast drawing minimum deviation value.
Step S09: by processor 20 minimum deviation value and permissible error value range are compared, judge whether minimum deviation value exceeds the permissible error value range.
Step S10: if minimum deviation value in the permissible error value range, then with the graphic collection taken for the K+2 time in classification corresponding to minimum deviation value.
Step S12: if minimum deviation value surpasses the permissible error value range, then set up the 3rd classification and with the image taken for the K+2 time as the 3rd comparison standard of classifying.
Step S13: show each classification results by display 85;
Wherein K is positive integer.
Above-mentioned planar graph aberration automatic detection device automatically snaps the planar graph of each workpiece, and according to default permissible error value range, planar array type digitizing, image blurring analysis and comparison with the grouping of classifying of each planar graph, and classification results is shown in display or directly prints, very directly perceived efficient.
For a person skilled in the art, can make other various corresponding changes and distortion according to technical scheme described above and design, and these all changes and distortion should belong within the protection domain of claim of the present invention all.
Claims (10)
1. planar graph aberration automatic detection device based on machine vision technique, it is characterized in that: it comprises video camera, storer, display and processor;
This video camera is used for taking the planar graph on some workpiece;
Processor is stored in storer with the image of shot by camera;
This display is used for each drawn classification results of video-stream processor;
Processor is preset with permissible error value range and classification number; Processor is set up the first classification and with the image taken for the 1st time comparison standard as the first classification; The image of taking for the K+1 time compared with the first standard of comparing of classifying draw deviate; Deviate and permissible error value range are compared, and whether the judgment bias value exceeds the permissible error value range; When deviate is in the permissible error value range, with graphic collection to the first classification of the K+1 time shooting; When deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying, wherein K is positive integer.
2. planar graph aberration automatic detection device as claimed in claim 1, it is characterized in that: after processor is set up the second classification, again the image of the K+2 time shooting and the standard of comparing of the first classification and the second classification are compared respectively, obtain respectively two deviates and contrast drawing minimum deviation value; Minimum deviation value and permissible error value range are compared, judge whether minimum deviation value exceeds the permissible error value range; If minimum deviation value is in the permissible error value range, then the image with the K+2 time shooting is integrated in classification corresponding to minimum deviation value; If minimum deviation value surpasses the permissible error value range, then set up the 3rd classification and with the image taken for the K+2 time as the 3rd comparison standard of classifying.
3. planar graph aberration automatic detection device as claimed in claim 1, it is characterized in that: before image is set up classification and comparison, processor will be stored in the characteristic index of comparing after the image digitazation of storer and calculate, wherein compare characteristic index calculating and comprise tone, brightness and saturation degree etc., the comparison characteristic index corresponding to image of the 1st time, the K+1 time and the K+2 time shooting that the classification comparison standard of the first to the 3rd classification is respectively video camera.
4. such as each described planar graph aberration automatic detection device in the claims 1 to 3, it is characterized in that: this planar graph aberration automatic detection device also comprises light-source box, photographic light sources, photoelectric sensor, travelling belt and is used for driving the conveyor drive of travelling belt;
Some workpiece are intervally arranged on travelling belt; Light-source box is the box body of an opening, and light-source box is located at travelling belt top, and the one side that light-source box has an opening faces travelling belt, and video camera is installed in the top in the light-source box, and photographic light sources is located in the photographic light sources case;
This photoelectric sensor is used for the detecting workpiece and enters light-source box and generate corresponding induced signal, and processor is taken the workpiece that enters in the light-source box according to the actuated signal control video camera that photoelectric sensor generates.
5. planar graph aberration automatic detection device as claimed in claim 4, it is characterized in that: this photographic light sources is the LED fluorescent light, and this LED fluorescent light is by DC power supply.
6. planar graph aberration automatic detection device as claimed in claim 5, it is characterized in that: this light-source box consists of by flat board and light shield are installed, video camera and LED fluorescent light are installed on this installation flat board, this installation is dull and stereotyped to become 30 degree to 60 degree angles with the end face of workpiece, scribble black coating or lining in this light shield with black Velveting.
7. planar graph aberration automatic detection device as claimed in claim 1, it is characterized in that: planar graph aberration automatic detection device also comprises the printer that is connected with processor.
8. planar graph aberration automatic testing method, it may further comprise the steps:
At the default aberration permissible error value range of processor and classification number;
Take planar graph on some workpiece by video camera;
The image of shot by camera is stored in storer;
Set up the first classification and with the image taken for the 1st time comparison standard as the first classification by processor;
By processor the image of taking for the K+1 time is compared with the first standard of comparing of classifying and to draw deviate;
By processor deviate and permissible error value range are compared, whether the judgment bias value exceeds the permissible error value range;
When deviate is in the permissible error value range, with graphic collection to the first classification of the K+1 time shooting;
When deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying;
Show each classification results by display;
Wherein K is positive integer.
9. planar graph aberration automatic testing method as claimed in claim 8, it is characterized in that: step " when deviate exceeds the permissible error value range, set up the second classification and with the image taken for the K+1 time as the second comparison standard of classifying " further comprising the steps of afterwards:
The image of the K+2 time shooting and the standard of comparing of the first classification and the second classification are compared respectively, obtain respectively two deviates and contrast drawing minimum deviation value;
By processor minimum deviation value and permissible error value range are compared, judge whether minimum deviation value exceeds the permissible error value range;
If minimum deviation value in the permissible error value range, then with the graphic collection taken for the K+2 time in classification corresponding to minimum deviation value;
If minimum deviation value surpasses the permissible error value range, then set up the 3rd classification and with the image taken for the K+2 time as the 3rd comparison standard of classifying.
10. planar graph aberration automatic testing method as claimed in claim 8 or 9, it is characterized in that: before image being set up classification and comparison, also comprise step " will be stored in the characteristic index of comparing after the image digitazation of storer calculates by processor ", wherein compare characteristic index calculating and comprise tone, brightness and saturation degree, the comparison characteristic index corresponding to image of the 1st time, the K+1 time and the K+2 time shooting that the classification comparison standard of the first to the 3rd classification is respectively video camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105294712A CN103033266A (en) | 2012-12-10 | 2012-12-10 | Automatic detection device and method of plane figure color shading |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105294712A CN103033266A (en) | 2012-12-10 | 2012-12-10 | Automatic detection device and method of plane figure color shading |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103033266A true CN103033266A (en) | 2013-04-10 |
Family
ID=48020398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105294712A Pending CN103033266A (en) | 2012-12-10 | 2012-12-10 | Automatic detection device and method of plane figure color shading |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103033266A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103364085A (en) * | 2013-07-22 | 2013-10-23 | 上海友浦塑胶有限公司 | Intelligent automatic color shading alarming device |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| CN104394385A (en) * | 2014-12-10 | 2015-03-04 | 华南师范大学 | Online detection device and detection method for ceramic tile quality |
| CN104964930A (en) * | 2015-06-03 | 2015-10-07 | 刘生全 | Liquid fuel corrosivity detection result determination method |
| CN106680286A (en) * | 2016-12-20 | 2017-05-17 | 深圳信息职业技术学院 | Machine vision-based laser processing system and machine vision-based laser processing method |
| CN109238459A (en) * | 2018-11-13 | 2019-01-18 | 惠州西电仲恺人工智能联合创新实验室有限公司 | The online vision detection system of LED luminance |
| CN110139904A (en) * | 2016-12-30 | 2019-08-16 | 涂层国外知识产权有限公司 | The system and method generated for formula information |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070046941A1 (en) * | 2005-08-24 | 2007-03-01 | Xerox Corporation | Spectrophotometer target distance variation compensation |
| CN101620179A (en) * | 2009-08-05 | 2010-01-06 | 燕山大学 | Scanning type glass color difference measuring device and measuring method thereof |
| CN201449292U (en) * | 2009-04-16 | 2010-05-05 | 程好学 | Automatic tile color separation device |
| CN102095499A (en) * | 2009-12-09 | 2011-06-15 | 程好学 | Method for automatic color separation of ceramic tiles |
| CN202267534U (en) * | 2011-10-24 | 2012-06-06 | 陕西理工学院 | Portable color detector |
-
2012
- 2012-12-10 CN CN2012105294712A patent/CN103033266A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070046941A1 (en) * | 2005-08-24 | 2007-03-01 | Xerox Corporation | Spectrophotometer target distance variation compensation |
| CN201449292U (en) * | 2009-04-16 | 2010-05-05 | 程好学 | Automatic tile color separation device |
| CN101620179A (en) * | 2009-08-05 | 2010-01-06 | 燕山大学 | Scanning type glass color difference measuring device and measuring method thereof |
| CN102095499A (en) * | 2009-12-09 | 2011-06-15 | 程好学 | Method for automatic color separation of ceramic tiles |
| CN202267534U (en) * | 2011-10-24 | 2012-06-06 | 陕西理工学院 | Portable color detector |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103364085A (en) * | 2013-07-22 | 2013-10-23 | 上海友浦塑胶有限公司 | Intelligent automatic color shading alarming device |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| CN103743486B (en) * | 2014-01-02 | 2015-12-02 | 上海大学 | A kind of automatic Grading System based on magnanimity tobacco leaf data and method |
| CN104394385A (en) * | 2014-12-10 | 2015-03-04 | 华南师范大学 | Online detection device and detection method for ceramic tile quality |
| CN104394385B (en) * | 2014-12-10 | 2018-08-31 | 华南师范大学 | A kind of ceramic tile quality on-line detecting device and its detection method |
| CN104964930A (en) * | 2015-06-03 | 2015-10-07 | 刘生全 | Liquid fuel corrosivity detection result determination method |
| CN104964930B (en) * | 2015-06-03 | 2018-03-02 | 刘生全 | A kind of decision method of liquid fuel corrosivity monitor result |
| CN106680286A (en) * | 2016-12-20 | 2017-05-17 | 深圳信息职业技术学院 | Machine vision-based laser processing system and machine vision-based laser processing method |
| CN110139904A (en) * | 2016-12-30 | 2019-08-16 | 涂层国外知识产权有限公司 | The system and method generated for formula information |
| CN109238459A (en) * | 2018-11-13 | 2019-01-18 | 惠州西电仲恺人工智能联合创新实验室有限公司 | The online vision detection system of LED luminance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103033266A (en) | Automatic detection device and method of plane figure color shading | |
| CN101882034B (en) | Device and method for discriminating color of touch pen of touch device | |
| CN102253048B (en) | Machine vision detection method and system for detection of various products | |
| CN108445007A (en) | A kind of detection method and its detection device based on image co-registration | |
| CN101424514B (en) | Band tape graduation on-line automatic detection system and method based on image processing | |
| US20190238741A1 (en) | Auxiliary apparatus for a digital imaging device | |
| CN110018172B (en) | Product detection system and method | |
| EP3505917B1 (en) | Colour grading process and system for diamonds | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN104792789A (en) | Chemical fiber paper tube appearance detection device and method | |
| CN102323272A (en) | Filter paper defect detecting system and detection method thereof based on machine vision technique | |
| CN114693676B (en) | Optical detection method and device for bleaching defects of new material textiles | |
| CN106204602B (en) | The anti-part detection method of element and system | |
| CN104392210A (en) | Gesture recognition method | |
| CN110186937A (en) | Reject mirror article surface two-dimensional defect detection method and system that dust influences | |
| CN202916012U (en) | Device for automatically detecting colour difference of plane figures | |
| CN109594319A (en) | A kind of pck count intelligent detection device and method | |
| CN112304876A (en) | Cotton color degree detection device and detection method based on machine vision | |
| CN202177587U (en) | Filter paper defect detecting system based on machine vision technology | |
| CN104766310B (en) | light source detection system and detection method | |
| CN202351182U (en) | Online high-speed detection system for defects on surface of tinplate | |
| CN102507008B (en) | Multi-template automatic optical color detection method | |
| CN203858032U (en) | Cloth color-difference detector | |
| CN207366475U (en) | A kind of relief pattern Online Video detection device | |
| CN210664378U (en) | Customized light source roughness detection device based on red-green chromatic aberration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130410 |