CN102680414A - Automatic grading device for red globe grapes based on machine vision and method thereof - Google Patents
Automatic grading device for red globe grapes based on machine vision and method thereof Download PDFInfo
- Publication number
- CN102680414A CN102680414A CN2012101719766A CN201210171976A CN102680414A CN 102680414 A CN102680414 A CN 102680414A CN 2012101719766 A CN2012101719766 A CN 2012101719766A CN 201210171976 A CN201210171976 A CN 201210171976A CN 102680414 A CN102680414 A CN 102680414A
- Authority
- CN
- China
- Prior art keywords
- image
- angle
- machine vision
- industrial camera
- red grape
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses an automatic grading device for red globe grapes based on a machine vision and a method thereof, relating to the technical field of fruit grading. The structure of the device is as follows: an airtight box and a lamp box are connected up and down to form an integral body, a circular hole is formed in a clapboard between the two boxes; a tablet computer is arranged on the sidewalls of the two boxes; an annular fluorescent lamp is internally arranged at the middle of the upper part of the lamp box, an industrial camera is internally arranged at the middle of the lower part of the airtight box, and a lens of an industrial camera rightly faces the circular hole; the industrial camera is connected with the tablet computer via a data wire; and the red globe grapes are placed in the lamp box. The automatic grading device and the method thereof disclosed by the invention can finish automatic grading by using a machine vision technology, as well as are uniform in standard, accurate in grading, high in efficiency due to the utilization of the computer for processing images, capable of realizing non-destructive testing grading, adaptive to the modern automatic detection industry due to a machine instead of human eyes, and good in application prospect and popularization prospect.
Description
Technical field
The present invention relates to the fruit grading technical field, relate in particular to automatic grading plant of a kind of red grape and method thereof based on machine vision.Specifically, the present invention utilizes machine vision technique to gather the image of red grape, through a series of Flame Image Process, carries out classification according to the size and the whole string color of red grape individual particle; For the classification of red grape, come into the market to provide a kind of means fast and effectively.
Background technology
For a long time, the classification of red grape is to rely on people's naked eyes to judge that subjective, classification work is uninteresting and loaded down with trivial details; And owing to the subjective judgement of criteria for classification from the people, different people's resolution standard varies especially, so error in classification is bigger.
The research of machine vision aspect is existing a lot, especially extensive especially aspect agricultural product Non-Destructive Testing and classification, yet the research of this type both at home and abroad is that object is studied with the single fruit target of regular shape such as orange, apple, tomato all mostly.And for red grape, because its out-of-shape, image segmentation and intractability are very big, both at home and abroad to the research of this type all seldom, also mainly are that size or form to whole string studied even have, and be then rarely found to the size discriminating of simple grain grape.
Utilize machine vision to come the size of judgment object of common occurrence.An Aiqin, Yu Zetong etc. measure the diameter of apple through to the apple Flame Image Process, thus according to size to apple classify (An Aiqin, Yu Zetong, Wang Hongqiang, 2008).Xiong Lirong, a chess-playing circles etc. extract and calculate the pixel count of simple grain peanut, and then have realized the classification (Xiong Lirong, a chess-playing circles, Xiao Renqin, 2007) to simple grain peanut size.Utilize Zhu Lianhai, Liu Muhua minimum rectangle method and centre of form Edge Distance method have realized the quick online detection classification (Zhu Lianhai, Liu Muhua, 2008) to the navel orange size.Like that, at present most utilize machine vision to carry out size to differentiate it all is, and relate to for the size discriminating few people of the single individuality in the such bunchiness object of red grape to single integral body.
Utilize machine vision that the research of red grape is rounded string mostly at present and be research object, research direction mainly concentrates on the Target Recognition and the prevention and control of plant diseases, pest control.For example, Tian Rui, Guo Yanling set about from the color characteristic of grape, have realized under natural scene the identification to grape, and the exploitation picking robot is had certain experiences meaning (Tian Rui, Guo Yanling, 2008).And the existing machine vision of utilizing is carried out grape in the research of classification, also is to carry out to the form of whole string.For example; People such as Chen Ying, Liao Tao uses projected area method and fruit direction of principal axis drop shadow curve to calculate the size and the form parameter of the whole string of grape; And then realization is to the quality classification of grape; The accuracy rate of color grading up to 90%, has then been reached 88.3% (Chen Ying, Liao Tao, woods just lean on etc., 2010) to the classification accuracy rate of size shape.
Through retrieval, domestic automatic classification technique of relevant red grape and the screening installation do not found as yet is applied to produce actual.
Summary of the invention
The object of the invention overcomes the problem that prior art exists with regard to being, automatic grading plant of a kind of red grape based on machine vision and method thereof are provided.
The objective of the invention is to realize like this:
The present invention utilizes machine vision, uses specific algorithm, and the image of red grape is cut apart calculating, the size of simple grain grape is differentiated, thereby realized objectifying of grape magnitude classification standard, the robotization of assorting process, the high efficiency of classification work.Adopt machine vision to carry out the magnitude classification of red grape, can from loaded down with trivial details uninteresting grape classification work, free the workman, increase work efficiency and accuracy, significance is arranged.
The present invention is primarily aimed at the red grape size and differentiates, different with other existing researchs is that the present invention classifies according to the size of simple grain in the whole string grape, but not puts in order the size of going here and there.In the present invention, several work below main the completion:
1, gather the image of bunchiness red grape, mainly comprise the selection of test with red grape, the preparation of test equipment is taken pictures etc.
2, seek appropriate algorithm, carry out Flame Image Process, extract characteristic parameter;
This is the most key place, is divided into two main steps, the firstth, and the image pre-service adopts suitable algorithm to realize cutting apart of grape and background; The secondth, the extraction of characteristic parameter and calculating, the border array is extracted on the border after utilization of the present invention is cut apart, and then the angle of curvature of every bit on the computation bound, differentiates the size of grape according to the mean value of the angle of curvature.
3, set up the red of different order of magnitude and carry automatic model of cognition, and check.
Emphasis of the present invention and difficult point are how to carry out the image pre-service and extract the standard of any characteristic parameter as classification, and this two closely bound up.The target that finally will realize is can extract reasonable parameter through the machine vision image technique, sets up the red size fractionation model of carrying, and realizes the size of harmless fast detecting red grape.
Specifically, technical scheme of the present invention is following:
One, based on the automatic grading plant of the red grape of machine vision (abbreviation device)
Like Fig. 1, this device is made up of lamp box, closed box, annular daylight lamp, industrial camera and panel computer;
Closed box and lamp box connect into an integral body up and down, and the dividing plate between two casees is provided with a circular hole; Two casees sidewall is provided with panel computer;
In the middle of the top of lamp box, be built-in with annular daylight lamp, in the middle of the bottom of closed box, be built-in with industrial camera, the camera of industrial camera is over against circular hole;
Industrial camera links to each other with panel computer through data line;
Red grape places lamp box.
Two, based on the red grape automatic grading method (abbreviation method) of machine vision
This method comprises the following steps:
1. red grape to be measured is numbered;
2. put into the closed box images acquired to red grape successively
One of every shooting is preserved and rename, with specific name sequence the image of gathering is classified;
In the image acquisition process, keep the clean and clean and tidy of background as far as possible, avoid making troubles to the image and the processing in later stage.
Each take 2~4, has clapped once after, with its upset, change the angle of putting, repeat shooting, thereby realization is from the information extraction as much as possible of red sage grape;
3. after images acquired is accomplished, write down image, image handled:
A, to figure image intensifying:
Through the conversion of gradation of image grade is stressed the characteristic paid close attention to reach, suppress the characteristic do not paid close attention to, picture quality is improved, quantity of information is enriched;
B, to image segmentation:
Through detecting the profile of object, object and background segment are come;
The characteristic parameter of C, extraction image:
The boundary curve degree of crook can reflect the size of simple grain grape indirectly, and boundary curve degree of crook measurement way the most intuitively is to use the curvature or the angle of curvature; Utilize the red profile of carrying of computer software search, and with the node of individual particle that individual particle is separated, calculate the average angle of curvature and average arc length line;
D, substitution model tormulation formula are judged the grape size;
Like Fig. 2, on (red grape) camber line, choose three some P
1, P, P
2, P wherein
1Arrive P and P to P
2Distance be equal, then the P angle of curvature of ordering is defined as vectorial P P
1With vectorial P
2The angle of P.
Said model tormulation formula is:
Principle of work of the present invention is:
The present invention has the following advantages and good effect:
1, adopts machine vision technique, can accomplish automatic classification;
2, standard is unified, and classification is accurate;
3, utilize the Computer Processing image, efficient is high;
4, can realize the Non-Destructive Testing classification;
5, replace human eye with machine, can adapt to modernization and detect industry automatically, have a good promotion prospects.
Description of drawings
Fig. 1 is the structural representation of this device, among the figure:
The 00-red grape,
The 10-lamp box, 11-lamp box side door;
The 20-closed box, 12-closed box roof door;
The 30-annular daylight lamp;
The 40-industrial camera, the 41-camera;
50-panel computer.
Fig. 2 is the specification of a model figure of red grape;
Fig. 3 is the workflow diagram of image processing software.
Embodiment
Specify below in conjunction with accompanying drawing and embodiment:
One, device
1, overall
Like Fig. 1, this device is made up of lamp box 10, closed box 20, annular daylight lamp 30, industrial camera 40 and panel computer 50;
In the middle of the top of lamp box 10, be built-in with annular daylight lamp 30, in the middle of the bottom of closed box 20, be built-in with industrial camera 40, the camera 41 of industrial camera 40 is over against circular hole K;
2, functional block
1) annular daylight lamp 30
As select Philips TLSC type annular daylight lamp for use; Its function is for red grape 00 light source to be provided.
2) industrial camera 40
As select the UI-2210RE-C-HG industrial camera for use; Its function is the view data of gathering red grape.
3) panel computer 50
Select D525 for use, cpu dominant frequency 1GHz, internal memory 1G, Lan/com/12-28v Adaptor.
Be built-in with image pick-up card and image processing software in the panel computer 50.
The workflow of described image processing software is:
1. reading images 1;
2. the RGB component is extracted in supplement, the gray-scale map computing, and histogram equalization is handled, and detects the edge, closed operation 2;
3. whether the surveyed area area is then to get into step 4. greater than 50003, otherwise continues step 3.;
4. only keep the zone greater than 5000, dilation operation rewrites and reads the RGB component, and the self-adaptation adjustment detects the edge, closed operation, filling cavity 4;
5. whether the surveyed area area is then to get into step 6. greater than 20005, otherwise continues step 5.;
6. only keep zone greater than 2000, closed operation, filling cavity is removed burr, extracts boundary information 6;
7. be divided into two types of calculating: computing curvature angle A; Calculate catastrophe point B;
Computing curvature angle A
Whether be infinitely great A1, be 1. A1 of repeating step then if 1. detecting the angle of curvature of asking, otherwise 2. A2 of entering step;
2. store this and put bent angle of curvature A2;
3. detecting whether finish A3, is then to get into 4. A4 of step, jumps to 1. A1 of step otherwise change;
4. ask average, output is A4 as a result;
5. set up and the inspection-classification MODEL C;
Calculate catastrophe point B
1. detect and adjacent become the angle at 3, be 1. B1 of repeating step then, otherwise get into 2. B2 of step whether greater than threshold value B1;
2. store this this point mutation point of some storage B2;
3. detecting whether finish B3, is then to get into 4. B4 of step, jumps to 1. B1 of step otherwise change;
4. extract the border total length, calculate the long B4 of average camber line;
5. set up and the inspection-classification MODEL C.
3, testing result
The test specimen of present embodiment is divided into two types with red grape by color available from the agricultural supermarket of China: red, aubergine; Be divided three classes by size: especially big, bigger than normal, less than normal.
The color judgment accuracy rate is 96%, and big or small correct judgment rate is 85%.
Claims (3)
1. automatic grading plant of the red grape based on machine vision is characterized in that:
Form by lamp box (10), closed box (20), annular daylight lamp (30), industrial camera (40) and panel computer (50);
Closed box (20) and lamp box (10) connect into an integral body up and down, and the dividing plate between two casees is provided with a circular hole (K); Two casees sidewall is provided with panel computer (50);
In the middle of the top of lamp box (10), be built-in with annular daylight lamp (30), in the middle of the bottom of closed box (20), be built-in with industrial camera (40), the camera (41) of industrial camera (40) is over against circular hole (K);
Industrial camera (40) links to each other with panel computer (50) through data line;
Red grape (00) places lamp box (10).
2. by the automatic grading plant of the described a kind of red grape of claim 1, it is characterized in that based on machine vision:
Described panel computer is built-in with image pick-up card and image processing software in (50), and the workflow of image processing software is:
1. reading images (1);
2. the RGB component is extracted in supplement, the gray-scale map computing, and histogram equalization is handled, and detects the edge, closed operation (2);
3. whether the surveyed area area is then to get into step 4. greater than 5000 (3), otherwise continues step 3.;
4. only keep the zone greater than 5000, dilation operation rewrites and reads the RGB component, and the self-adaptation adjustment detects the edge, closed operation, filling cavity (4);
5. whether the surveyed area area is then to get into step 6. greater than 2000 (5), otherwise continues step 5.;
6. only keep zone greater than 2000, closed operation, filling cavity is removed burr, extracts boundary information 6;
7. be divided into two types of calculating: computing curvature angle (A); Calculate catastrophe point (B);
Computing curvature angle (A)
Whether be infinitely great (A1), be repeating step 1. (A1) then, otherwise get into step 2. (A2) if 1. detecting institute's angle of curvature of asking;
2. store this and put the bent angle of curvature (A2);
3. detecting whether finish (A3), is then to get into step 4. (A4), jumps to step 1. (A1) otherwise change;
4. ask average, output result (A4);
5. set up and inspection-classification model (C);
Calculate catastrophe point (B)
1. detect and adjacent become the angle at 3, be repeating step 1. (B1) then, otherwise get into step 2. (B2) whether greater than threshold value (B1);
2. store this this point mutation point (B2) of some storage;
3. detecting whether finish (B3), is then to get into step 4. (B4), jumps to step 1. (B1) otherwise change;
4. extract the border total length, calculate average camber line long (B4);
5. set up and inspection-classification model (C).
3. by the method for the described a kind of automatic grading plant of red grape based on machine vision of claim 1, it is characterized in that:
1. red grape to be measured is numbered;
2. put into the closed box images acquired to red grape successively
One of every shooting is preserved and rename, with specific name sequence the image of gathering is classified;
Each take 2~4, has clapped once after, with its upset, the angle that change is put repeats shooting;
3. after images acquired is accomplished, write down image, image handled:
A, to figure image intensifying:
Through the conversion of gradation of image grade is stressed the characteristic paid close attention to reach, suppress the characteristic do not paid close attention to, picture quality is improved, quantity of information is enriched;
B, to image segmentation:
Through detecting the profile of object, object and background segment are come;
The characteristic parameter of C, extraction image:
Utilize the red profile of carrying of computer software search, and with the node of individual particle that individual particle is separated, calculate the average angle of curvature and average arc length line;
D, substitution model tormulation formula are judged the grape size;
Said model tormulation formula is:
θ: the angle of curvature; A: vectorial P P
1B: vectorial P
2P.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210171976.6A CN102680414B (en) | 2012-05-30 | 2012-05-30 | Automatic grading device for red globe grapes based on machine vision and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210171976.6A CN102680414B (en) | 2012-05-30 | 2012-05-30 | Automatic grading device for red globe grapes based on machine vision and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102680414A true CN102680414A (en) | 2012-09-19 |
CN102680414B CN102680414B (en) | 2014-06-25 |
Family
ID=46812676
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210171976.6A Expired - Fee Related CN102680414B (en) | 2012-05-30 | 2012-05-30 | Automatic grading device for red globe grapes based on machine vision and method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102680414B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103148781A (en) * | 2013-01-26 | 2013-06-12 | 广西工学院鹿山学院 | Grapefruit size estimating method based on binocular vision |
CN103162627A (en) * | 2013-03-28 | 2013-06-19 | 广西工学院鹿山学院 | Method for estimating fruit size by citrus fruit peel mirror reflection |
CN103487374A (en) * | 2013-10-14 | 2014-01-01 | 无锡艾科瑞思产品设计与研究有限公司 | Machine-vision-based device and method for qualitatively and rapidly detecting clenbuterol |
CN105203543A (en) * | 2015-09-22 | 2015-12-30 | 华中农业大学 | Machine vision based whole case red grape fruit size grading device and method |
CN105466866A (en) * | 2014-09-03 | 2016-04-06 | 上海市闵行第二中学 | Visible light spectrophotometer |
GB2531414A (en) * | 2014-08-14 | 2016-04-20 | Kenwood Ltd | Food preparation |
CN105548031A (en) * | 2015-12-18 | 2016-05-04 | 北京农业智能装备技术研究中心 | Mobile-terminal-based soil type identification apparatus |
CN107862326A (en) * | 2017-10-30 | 2018-03-30 | 昆明理工大学 | A kind of transparent apple recognition methods based on full convolutional neural networks |
CN109827971A (en) * | 2019-03-19 | 2019-05-31 | 湖州灵粮生态农业有限公司 | A kind of method of non-destructive testing fruit surface defect |
CN110006899A (en) * | 2019-04-12 | 2019-07-12 | 华中农业大学 | The lossless vision detection and classification method of lime-preserved egg inside quality |
CN113820322A (en) * | 2021-10-20 | 2021-12-21 | 河北农业大学 | Detection device and method for seed appearance quality |
CN114354628A (en) * | 2022-01-05 | 2022-04-15 | 威海若维信息科技有限公司 | Root agricultural product defect detection method based on machine vision |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2587534Y (en) * | 2002-12-27 | 2003-11-26 | 浙江大学 | Machine vision based fruit sorting machine |
US6957940B2 (en) * | 2003-03-25 | 2005-10-25 | Materiel Pour L'arboriculture Fruitiere | Unit for sorting and packaging products capable of being hung on a hooking member for the purpose of their conveyance, such as bunches of fruits, in particular table grapes or truss tomatoes |
CN101561402B (en) * | 2009-05-07 | 2011-06-22 | 浙江大学 | Machine vision-based real-time detection and grading method and grading device for pork appearance quality |
CN202599818U (en) * | 2012-05-30 | 2012-12-12 | 华中农业大学 | Machine vision-based red globe grape automatic-classifying device |
-
2012
- 2012-05-30 CN CN201210171976.6A patent/CN102680414B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2587534Y (en) * | 2002-12-27 | 2003-11-26 | 浙江大学 | Machine vision based fruit sorting machine |
US6957940B2 (en) * | 2003-03-25 | 2005-10-25 | Materiel Pour L'arboriculture Fruitiere | Unit for sorting and packaging products capable of being hung on a hooking member for the purpose of their conveyance, such as bunches of fruits, in particular table grapes or truss tomatoes |
CN101561402B (en) * | 2009-05-07 | 2011-06-22 | 浙江大学 | Machine vision-based real-time detection and grading method and grading device for pork appearance quality |
CN202599818U (en) * | 2012-05-30 | 2012-12-12 | 华中农业大学 | Machine vision-based red globe grape automatic-classifying device |
Non-Patent Citations (3)
Title |
---|
王巧华等: "基于图像识别的农产品品质无损检测", 《湖北农业科学》 * |
王巧华等: "我国机器视觉技术的发展前沿", 《农机化研究》 * |
陈英等: "基于计算机视觉的葡萄检测分级系统", 《农业机械学报》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103148781A (en) * | 2013-01-26 | 2013-06-12 | 广西工学院鹿山学院 | Grapefruit size estimating method based on binocular vision |
CN103162627A (en) * | 2013-03-28 | 2013-06-19 | 广西工学院鹿山学院 | Method for estimating fruit size by citrus fruit peel mirror reflection |
CN103487374B (en) * | 2013-10-14 | 2016-03-30 | 无锡艾科瑞思产品设计与研究有限公司 | The qualitative device for fast detecting of clenbuterol hydrochloride based on machine vision and method |
CN103487374A (en) * | 2013-10-14 | 2014-01-01 | 无锡艾科瑞思产品设计与研究有限公司 | Machine-vision-based device and method for qualitatively and rapidly detecting clenbuterol |
GB2531414B (en) * | 2014-08-14 | 2021-01-27 | Kenwood Ltd | Food preparation |
GB2531414A (en) * | 2014-08-14 | 2016-04-20 | Kenwood Ltd | Food preparation |
US10635921B2 (en) | 2014-08-14 | 2020-04-28 | Kenwood Limited | Food container system and method |
CN105466866A (en) * | 2014-09-03 | 2016-04-06 | 上海市闵行第二中学 | Visible light spectrophotometer |
CN105203543A (en) * | 2015-09-22 | 2015-12-30 | 华中农业大学 | Machine vision based whole case red grape fruit size grading device and method |
CN105548031A (en) * | 2015-12-18 | 2016-05-04 | 北京农业智能装备技术研究中心 | Mobile-terminal-based soil type identification apparatus |
CN107862326A (en) * | 2017-10-30 | 2018-03-30 | 昆明理工大学 | A kind of transparent apple recognition methods based on full convolutional neural networks |
CN109827971A (en) * | 2019-03-19 | 2019-05-31 | 湖州灵粮生态农业有限公司 | A kind of method of non-destructive testing fruit surface defect |
CN110006899A (en) * | 2019-04-12 | 2019-07-12 | 华中农业大学 | The lossless vision detection and classification method of lime-preserved egg inside quality |
CN113820322A (en) * | 2021-10-20 | 2021-12-21 | 河北农业大学 | Detection device and method for seed appearance quality |
CN113820322B (en) * | 2021-10-20 | 2023-12-26 | 河北农业大学 | Detection device and method for appearance quality of seeds |
CN114354628A (en) * | 2022-01-05 | 2022-04-15 | 威海若维信息科技有限公司 | Root agricultural product defect detection method based on machine vision |
CN114354628B (en) * | 2022-01-05 | 2023-10-27 | 威海若维信息科技有限公司 | Rhizome agricultural product defect detection method based on machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN102680414B (en) | 2014-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102680414B (en) | Automatic grading device for red globe grapes based on machine vision and method thereof | |
CN105203543B (en) | FCL red grape fruit size fractionation devices and methods therefor based on machine vision | |
CN105139386B (en) | A kind of image processing method of fast automatic detecting electric connector solder joint defective work | |
CN105046700B (en) | Fruit surface defect detection method and system based on gamma correction and color classification | |
CN104766097B (en) | Surface of aluminum plate defect classification method based on BP neural network and SVMs | |
CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
CN108230307B (en) | Corn broken grain detection method based on contour centroid distance and neural network | |
CN104990892B (en) | The spectrum picture Undamaged determination method for establishing model and seeds idenmtification method of seed | |
CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
TWI642126B (en) | Semiconductor wafer analyzing sytem and method thereof | |
CN112893159B (en) | Coal gangue sorting method based on image recognition | |
CN111652883B (en) | Glass surface defect detection method based on deep learning | |
CN108672316A (en) | A kind of micro parts quality detecting system based on convolutional neural networks | |
CN202599818U (en) | Machine vision-based red globe grape automatic-classifying device | |
CN106442561A (en) | Online image acquisition system for detecting citrus skin defects and method | |
CN103177266A (en) | Intelligent stock pest identification system | |
CN106872473A (en) | A kind of potato defects detection identifying system design based on machine vision | |
US20230360411A1 (en) | Cherry picking and classifying method and device based on machine vision | |
CN110575973B (en) | Crop seed quality detection and screening system | |
CN107576660B (en) | A kind of double yellow duck egg Automatic Visual Inspection method based on apart from contour | |
CN109446964A (en) | Face detection analysis method and device based on end-to-end single-stage multiple scale detecting device | |
CN102495067B (en) | System for identifying impurities of edible funguses on line | |
CN103245666A (en) | Automatic detecting method for appearance defects of storage battery polar plate | |
Sidehabi et al. | The Development of Machine Vision System for Sorting Passion Fruit using Multi-Class Support Vector Machine. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140625 |
|
CF01 | Termination of patent right due to non-payment of annual fee |