CN108491892A - fruit sorting system based on machine vision - Google Patents
fruit sorting system based on machine vision Download PDFInfo
- Publication number
- CN108491892A CN108491892A CN201810302547.5A CN201810302547A CN108491892A CN 108491892 A CN108491892 A CN 108491892A CN 201810302547 A CN201810302547 A CN 201810302547A CN 108491892 A CN108491892 A CN 108491892A
- Authority
- CN
- China
- Prior art keywords
- fruit
- image
- camera
- machine vision
- sorting system
- 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
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 15
- 241001292396 Cirrhitidae Species 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004040 coloring Methods 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000013316 zoning Methods 0.000 claims description 2
- 238000001444 catalytic combustion detection Methods 0.000 claims 1
- 239000000284 extract Substances 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 15
- 238000005498 polishing Methods 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 abstract 2
- 239000006002 Pepper Substances 0.000 abstract 1
- 230000033772 system development Effects 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/009—Sorting of fruit
Abstract
The design realizes fruit sorting work using machine vision technique in terms of hardware design type selecting and software system development two, including:Design selection machine vision industrial camera, camera lens and polishing scheme ensure the acquisition high quality fruit image that fruit sorting system can be continual and steady;Salt-pepper noise present in fruit image, Gaussian noise are inhibited using medium filtering and binomial filtering.The marginal information of fruit image is highlighted using unsharp mask method simultaneously;Fruit classification is realized using supervised gauss hybrid models clustering algorithm;The data of monocular camera guided robot crawl are calibrated by Zhang Zhengyou standardizations and practical crawl pose is calculated.
Description
Technical field
This system is the application that machine vision sorts link in fruit, belongs to image procossing and field of machine vision, is related to
Halcon softwares, and in particular to the classification and sorting work of fruit.
Background technology
Most recent two decades, machine vision technique have obtained largely developing, especially in industry and agricultural production side
Face gradually shows the trend that substitution manually carries out high-risk, high intensity, repeats miscellaneous work.This depends primarily on machine and regards
Feel the peculiar advantage shown.First, machine vision technique is that industrial production line increases vision non-contact type sensor, from
Side improves the flexibility of production.Secondly, a large amount of production information is carry in visual pattern, passes through the analysis to target image
Desired creation data can be obtained under cordless.Finally, using machine vision technique be not present be similar to it is artificial because
The problem of sorting efficiency caused by fatigue declines.
Invention content
The present invention provides a kind of based on machine vision to realize that machine replaces the work for being accomplished manually fruit sorting
Method for sorting, the system include image collecting device, fruit transmission device, human-computer interaction interface, image pre-processing module, fruit
Classification and level identification module, fruit sort module;Specifically detection method step is:
A, Image Acquisition;B, image preprocessing;C, types of fruits judges;D, level identification;E, monocular camera hand and eye calibrating;F, water
Fruit is sorted.
The function of the image collecting device is:According to reality of work working space and operating distance, selection is suitable
Industrial camera and camera lens, the position and angle for adjusting camera obtain fruit image, complete the real-time acquisition of image.Fruit transmission dress
The function of setting is:In conjunction with the parameter that human-computer interaction interface is arranged, cooperation PLC controls conveyer belt, completes the transport of fruit.People
The function of machine interactive interface is:The start-stop mode and transmission speed of transmission device are set.The function of image pre-processing module is:
The inhibition work to the random noise in former fruit image is completed by the combination of median filter and binomial filter.Image
The machine vision algorithm packet with standard that processing software is developed using Germany MVtec companies possesses widely used machine and regards
Feel the HALCON softwares of Integrated Development Environment.Fruit is classified and the function of level identification module is:It is used for by training set training
The gauss hybrid models grader of fruit classification, fruit transverse diameter is calculated in conjunction with pixel actual physics distance(Unit:cm)Greatly
The small judgement for completing fruit variety and level identification.Fruit sorting module function be:Receive point of fruit by serial communication
The location information of class and fruit and guides robot to complete fruit crawl.
In system noted earlier, preferred embodiment is that the equipment that the step A is used has camera bellows, mega pixel level industry phase
Machine and camera lens, annular light source and industrial personal computer;Industrial camera and camera lens are fixed on annular light source cooperation in camera bellows, are mended by light source
Light cooperation camera can obtain clearly fruit image, and being sent to industrial personal computer by gigabit Network Communication is handled;The video camera
Camera and camera lens select dimensional view as the clear industrial camera of MV-EM120M/C area array CCD color high-definitions and AFT-1214MP respectively
Industrial lens.
In system noted earlier, preferred embodiment is that the step B selects median filter and binomial filter to combine
Method is completed to the noise suppressed in fruit original image.Then the enhancing of fruit contour edge is realized by unsharp mask method.Most
Fruit is extracted from background using global automatic threshold segmentation afterwards.
In system noted earlier, preferred embodiment is that the step C extraction fruit surface colors and provincial characteristics establish fruit
Characteristic of division vector clusters gauss hybrid models algorithm by training supervised and generates Machine learning classifiers, realizes fruit
Intelligent classification.
C1, the colouring information and area information that fruit is obtained by global threshold partitioning algorithm, establish be based on color respectively
The classifier training collection of feature and provincial characteristics.
C2, two supervised cluster gauss hybrid models graders are created, uses color characteristic training set and region respectively
Feature training set completes classifier training, establishes classification boundaries.
C3, it is extracted in image using based on the collected entire image of color characteristic gauss hybrid models grader extraction
Fruit profile and fruit color information.
C4, using the fruit profile zoning feature in C3 steps, imported into the grader based on provincial characteristics and sentence
Other types of fruits.
In system noted earlier, preferred embodiment is that the step D is as follows:
D1, the fruit region judged after fruit classification is obtained(Resion)Information;
D2, the actual physics distance for calculating image pixel;
D3, the external ellipse of fruit is drawn according to fruit information, choose ellipse short shaft length and be used as fruit transverse diameter, fruit reality is calculated
Border transverse diameter length and divided rank.
In system noted earlier, preferred embodiment is that it is 7 × 7 that the step E, which selects 100 × 100mm, pattern matrix, black
Dot radius is 2mm, and dot centre distance is the center of circle display type plane reference template of 8mm, based on Zhang Zhengyou standardizations,
Shown in being as follows:
E1, acquisition 9-16 width scaling board images, the interior zone of scaling board is found by Threshold segmentation;
E2, the edge of each dot of scaling board is obtained by sub-pixel edge extracting method, is fitted and is obtained by Least Square Circle
The central coordinate of circle of dot determines correspondence between central coordinate of circle and they project in the picture and scaling board and video camera
Between rough position relationship, the i.e. outer ginseng initial value of video camera;
E3, Halcon library functions are called to determine intrinsic parameter, outer parameter after the correction of camera;Finally, it is averaged by repeatedly measuring
Value determines relevant parameter information.
In system noted earlier, preferred embodiment is that the step F is as follows:
F1,3D reference axis are drawn out in fruit image, and the profile according to fruit color classification finds out its sub-pixel edge
Centre coordinate is used as the centre coordinate of crawl fruit;
F2, the image coordinate value extracted is converted to physical coordinates system coordinate using nominal data;
F3, all fruit centers are acquired in image in the physical location of robot basis coordinates system, is sent to robot and completes crawl.
Compared with prior art, it is the advantages of the design:
1, the camera of NI Vision Builder for Automated Inspection, camera lens and polishing scheme are designed in the hardware design part of system one by one
And type selecting.The standard set machine vision algorithm packet of German MVtec companies exploitation has been selected in this system Software for Design part
(HALCON machine vision softwares)As Software Development Platform, the processing to fruit image and classification sorting work are completed.
2, the design uses the gauss hybrid models algorithm based on machine learning.According to gauss hybrid models grader and
Bayesian decision criterion is capable of the kind and colouring information for distinguishing fruit of intelligence, special by color to fruit and region
The clustering learning of sign trains the classification task that corresponding fruit classifier completes unknown fruit image.The grader is for portion
Dtex levies apparent fruit(Such as:Orange)Classification accuracy can reach 100%, and overall classification accuracy is up to 98% or more.This is
Various fruit are divided into large, medium and small three grades by system fruit grading link using fruit transverse diameter size as criterion.
3, system studies the pose evaluation work that monocular camera guided robot captures, by using just
Friendly standardization carries out the hand and eye calibrating of camera, obtains the inside and outside parameter of camera, has then calculated fruit using nominal data
Accurate world coordinates has done preparation for the manipulator crawl sorting of fruit.The final calibration error of coordinate of system can be controlled
System is between 0.7-1.5mm.
Description of the drawings
Fig. 1 is the NI Vision Builder for Automated Inspection schematic diagram of the design.
Fig. 2 is the Technology Roadmap of the design.
Wherein 1 is camera, and 2 be light source, and 3 be computer, and 4 be determinand.
Specific implementation mode
The technical solution of the design is described in detail with reference to embodiment and experimental example, but protection domain is without being limited thereto.
A kind of image processing system of fruit sorting system and this method of realization based on machine vision of embodiment, from
And it realizes machine and replaces the link manually produced.
Image processing system schematic diagram includes examined object, light source, optical lens, industrial camera, photoelectric sensor, phase
Machine and computer interface, computer, image processing software and transmission device.
Fig. 1 is the systematic schematic diagram of the design comprising:
The original image of fruit is obtained by the combination of camera after type selecting and camera lens;
The digital picture of fruit is sent to computer storage by camera and computer interface;
Image processing software is the Halcon softwares mounted on computer-internal, and the fruit original image for that will acquire carries out ash
Degreeization, noise suppressed, Threshold segmentation, feature extraction, based on gauss hybrid models classification, level identification and sorting pose calculate etc.
Processing;
Fig. 2 is the Technology Roadmap of the design, which includes the following steps:
A, system hardware type selecting, specific steps:By calculating the camera minimum field range in actual working environment, camera lens work
The optical band of distance and light source chooses suitable industrial camera, camera lens, mating polishing scheme and determines material crawl dress respectively
It sets.The camera and camera lens are MV-EM120M/C area array cameras and AFT-1214MP industrial camera lens, and fruit grabbing device is
IRB-120 six-joint robots;
B, Image Acquisition uses the asynchronous image acquisition modality that Halcon is provided, and improves real-time performance of the program;
C, image preprocessing is as follows shown:
C1, the original fruit image of acquisition realize fruit image gray processing by channel selecting using third channel component image;
C2, the inhibition of the random noise in fruit image is completed by choosing median filter and the cooperation of binomial filter;
C3, fruit marginal information, the bianry image of global automatic threshold segmentation extraction fruit are protruded using unsharp mask method.
D, fruit classification and level identification are as follows shown:
D1, the colouring information and area characteristic information that fruit is extracted using the fruit bianry image information extracted as mask, point
It Chuan Jian not color characteristic training set and provincial characteristics training set;
D2, the grader based on gauss hybrid models is created using Halcon;
D3, according to the fruit color and provincial characteristics training set in D1, gauss hybrid models graders is trained successively, then to surveying
Examination concentrates fruit to classify.
E, fruit crawl pose calculates, and is as follows shown:
E1, acquisition 9-16 width scaling board images, the interior zone of scaling board is found by Threshold segmentation;
E2, the edge of each dot of scaling board is obtained by sub-pixel edge extracting method, is fitted and is obtained by Least Square Circle
The central coordinate of circle of dot determines correspondence between central coordinate of circle and they project in the picture and scaling board and video camera
Between rough position relationship, the i.e. outer ginseng initial value of video camera;
E3, Halcon library functions are called to determine intrinsic parameter, outer parameter after the correction of camera;Finally, it is averaged by repeatedly measuring
Value determines relevant parameter information.
E4, the fruit region gone out using color feature extracted profile information obtain fruit image centroid pixel coordinate, so
Afterwards this world coordinates value is calculated according to calibration result.
It should be pointed out that specific implementation mode is the more representational example of the design, it is clear that the skill of the design
Art scheme is not limited to the above embodiments, and can also have many variations.Those skilled in the art define public affairs with the design
Written description open or according to file is undoubted to be obtained, and this patent scope of the claimed is considered as.
Claims (7)
1. the fruit sorting system based on machine vision, chief component include:Image collecting device, fruit transmission dress
It sets, module is sorted in the classification of human-computer interaction interface, image pre-processing module, fruit and level identification module, fruit;System operation
Specifically detecting step is:
A, Image Acquisition;B, image preprocessing;C, types of fruits judges;D, level identification;E, monocular camera hand and eye calibrating;F, water
Fruit is sorted.
2. the fruit sorting system based on machine vision as described in claim 1, it is characterised in that:What the step A was used sets
Have camera bellows, mega pixel level industrial camera and camera lens, annular light source and industrial personal computer;Industrial camera and camera lens are matched with annular light source
Conjunction is fixed in camera bellows, is coordinated camera that can obtain clearly fruit image by light source light filling, is sent to by gigabit Network Communication
Industrial personal computer is handled;The camera and camera lens of the video camera select dimensional view colored as MV-EM120M/C area array CCDs respectively
High-resolution industrial camera and AFT-1214MP industrial lens.
3. the fruit sorting system based on machine vision as described in claim 1, it is characterised in that:The step B selects intermediate value
The method that filter and binomial filter combine is completed, to the noise suppressed in fruit original image, then to pass through unsharp mask
Method realizes the enhancing of fruit contour edge, is finally extracted fruit from background using global automatic threshold segmentation.
4. the fruit sorting system based on machine vision as described in claim 1, it is characterised in that:The step C extracts fruit
Surface color and provincial characteristics establish fruit characteristic of division vector, and clustering gauss hybrid models algorithm by training supervised generates
Machine learning classifiers realize the intelligent classification of fruit;It is as follows:
C1, the colouring information and area information that fruit is obtained by global threshold partitioning algorithm, establish be based on color characteristic respectively
With the classifier training collection of provincial characteristics;
C2, two supervised cluster gauss hybrid models graders are created, uses color characteristic training set and provincial characteristics respectively
Training set completes classifier training, establishes classification boundaries;
C3, fruit in image is extracted using based on the collected entire image of color characteristic gauss hybrid models grader extraction
Profile and fruit color information;
C4, using the fruit profile zoning feature in C3 steps, imported into the grader based on provincial characteristics and differentiate water
Fruit type.
5. the fruit sorting system based on machine vision as described in claim 1, it is characterised in that:The step D specific steps
It is as follows:
D1, the fruit region judged after fruit classification is obtained(Resion)Information;
D2, the actual physics distance for calculating image pixel;
D3, the external ellipse of fruit is drawn according to fruit information, choose ellipse short shaft length and be used as fruit transverse diameter, fruit reality is calculated
Border transverse diameter length and divided rank.
6. the fruit sorting system based on machine vision as described in claim 1, it is characterised in that:The step E selections 100 ×
100mm, pattern matrix are 7 × 7, and dark circles point radius is 2mm, and dot centre distance is the center of circle display type plane reference of 8mm
Template is as follows shown based on Zhang Zhengyou standardizations:
E1, acquisition 9-16 width scaling board images, the interior zone of scaling board is found by Threshold segmentation;
E2, the edge of each dot of scaling board is obtained by sub-pixel edge extracting method, is fitted and is obtained by Least Square Circle
The central coordinate of circle of dot determines correspondence between central coordinate of circle and they project in the picture and scaling board and video camera
Between rough position relationship, the i.e. outer ginseng initial value of video camera;
E3, Halcon library functions are called to determine intrinsic parameter, outer parameter after the correction of camera;Finally, it is averaged by repeatedly measuring
Value determines relevant parameter information.
7. the fruit sorting system based on machine vision as described in claim 1, it is characterised in that:The step F specific steps
It is as follows:
F1,3D reference axis are drawn out in fruit image, and the profile according to fruit color classification finds out its sub-pixel edge
Centre coordinate is used as the centre coordinate of crawl fruit;
F2, the image coordinate value extracted is converted to physical coordinates system coordinate using nominal data;
F3, all fruit centers are acquired in image in the physical location of robot basis coordinates system, is sent to robot and completes crawl.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810302547.5A CN108491892A (en) | 2018-04-05 | 2018-04-05 | fruit sorting system based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810302547.5A CN108491892A (en) | 2018-04-05 | 2018-04-05 | fruit sorting system based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108491892A true CN108491892A (en) | 2018-09-04 |
Family
ID=63314660
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810302547.5A Pending CN108491892A (en) | 2018-04-05 | 2018-04-05 | fruit sorting system based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108491892A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255757A (en) * | 2018-04-25 | 2019-01-22 | 江苏大学 | A kind of machine vision places grape cluster carpopodium region segmentation method naturally |
CN109740681A (en) * | 2019-01-08 | 2019-05-10 | 南方科技大学 | A kind of fruit method for sorting, device, system, terminal and storage medium |
CN109926348A (en) * | 2018-12-03 | 2019-06-25 | 广东技术师范大学 | One kind being based on RGB fruit classification method and sorter |
CN110110760A (en) * | 2019-04-17 | 2019-08-09 | 浙江工业大学 | A kind of workpiece positioning and recognition methods based on machine vision |
CN110146516A (en) * | 2019-06-17 | 2019-08-20 | 湖南农业大学 | Fruit sorter based on orthogonal binocular machine vision |
CN110170456A (en) * | 2019-04-30 | 2019-08-27 | 南京邮电大学 | Fruit sorting equipment based on image procossing |
CN110174065A (en) * | 2019-06-17 | 2019-08-27 | 湖南农业大学 | Fruit size lossless detection method based on orthogonal binocular machine vision |
CN110276386A (en) * | 2019-06-11 | 2019-09-24 | 济南大学 | A kind of apple grading method and system based on machine vision |
CN110298885A (en) * | 2019-06-18 | 2019-10-01 | 仲恺农业工程学院 | A kind of stereoscopic vision recognition methods of Non-smooth surface globoid target and positioning clamping detection device and its application |
CN110788024A (en) * | 2019-11-13 | 2020-02-14 | 苏州大成有方数据科技有限公司 | Automatic sorting system for intelligent manufacturing and working method thereof |
CN111242057A (en) * | 2020-01-16 | 2020-06-05 | 南京理工大学 | Product sorting system, method, computer device and storage medium |
CN112241747A (en) * | 2019-07-16 | 2021-01-19 | 顺丰科技有限公司 | Object sorting method, device, sorting equipment and storage medium |
CN112329296A (en) * | 2020-10-28 | 2021-02-05 | 天河超级计算淮海分中心 | Fruit mechanical damage calculation method and device, computer equipment and storage medium |
CN112607100A (en) * | 2020-11-22 | 2021-04-06 | 泰州市华仕达机械制造有限公司 | Compatible fruit conveying and distributing system |
CN113145473A (en) * | 2021-02-20 | 2021-07-23 | 广州大学华软软件学院 | Intelligent fruit sorting system and method |
DE102020209937A1 (en) | 2020-08-06 | 2022-02-10 | Bosch Limited | PROCEDURE FOR COUNTING AND CLASSIFICATION OF PRODUCTS USING COMPUTER VISION |
CN114273240A (en) * | 2020-09-27 | 2022-04-05 | 深圳顺丰泰森控股(集团)有限公司 | Express delivery single piece separation method, device and system and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101912847A (en) * | 2010-08-02 | 2010-12-15 | 扬州福尔喜果蔬汁机械有限公司 | Fruit grading system and method based on DSP machine vision |
US20110286637A1 (en) * | 2008-10-10 | 2011-11-24 | Christiaan Fivez | Method for assigning a stonefruit to a predetermined class and a device therefor |
CN202778994U (en) * | 2012-07-10 | 2013-03-13 | 杨玉蒙 | Automatic sorting and conveying device for fruits |
US20130083974A1 (en) * | 2011-09-29 | 2013-04-04 | National Tsing Hua University | Image method for classifying insects and classifying process for insects |
CN103949409A (en) * | 2014-04-21 | 2014-07-30 | 三峡大学 | Automatic fruit sorting system |
CN107185859A (en) * | 2017-06-22 | 2017-09-22 | 陕西理工大学 | A kind of citrus sorting equipment based on image procossing |
CN107330478A (en) * | 2017-07-24 | 2017-11-07 | 广东工业大学 | A kind of cherry tomato sorting technique, system and cherry tomato on-line sorting system |
CN107694962A (en) * | 2017-11-07 | 2018-02-16 | 陕西科技大学 | A kind of fruit automatic sorting method based on machine vision and BP neural network |
-
2018
- 2018-04-05 CN CN201810302547.5A patent/CN108491892A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110286637A1 (en) * | 2008-10-10 | 2011-11-24 | Christiaan Fivez | Method for assigning a stonefruit to a predetermined class and a device therefor |
CN101912847A (en) * | 2010-08-02 | 2010-12-15 | 扬州福尔喜果蔬汁机械有限公司 | Fruit grading system and method based on DSP machine vision |
US20130083974A1 (en) * | 2011-09-29 | 2013-04-04 | National Tsing Hua University | Image method for classifying insects and classifying process for insects |
CN202778994U (en) * | 2012-07-10 | 2013-03-13 | 杨玉蒙 | Automatic sorting and conveying device for fruits |
CN103949409A (en) * | 2014-04-21 | 2014-07-30 | 三峡大学 | Automatic fruit sorting system |
CN107185859A (en) * | 2017-06-22 | 2017-09-22 | 陕西理工大学 | A kind of citrus sorting equipment based on image procossing |
CN107330478A (en) * | 2017-07-24 | 2017-11-07 | 广东工业大学 | A kind of cherry tomato sorting technique, system and cherry tomato on-line sorting system |
CN107694962A (en) * | 2017-11-07 | 2018-02-16 | 陕西科技大学 | A kind of fruit automatic sorting method based on machine vision and BP neural network |
Non-Patent Citations (2)
Title |
---|
焦恩璋等: "工业机器人分拣技术的实现", 《组合机床与自动化加工技术》 * |
薄雪峰等: "基于立体视觉的虹膜膨隆三维信息的实验方法探索", 《北京生物医学工程》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255757B (en) * | 2018-04-25 | 2022-01-11 | 江苏大学 | Method for segmenting fruit stem region of grape bunch naturally placed by machine vision |
CN109255757A (en) * | 2018-04-25 | 2019-01-22 | 江苏大学 | A kind of machine vision places grape cluster carpopodium region segmentation method naturally |
CN109926348A (en) * | 2018-12-03 | 2019-06-25 | 广东技术师范大学 | One kind being based on RGB fruit classification method and sorter |
CN109740681A (en) * | 2019-01-08 | 2019-05-10 | 南方科技大学 | A kind of fruit method for sorting, device, system, terminal and storage medium |
CN110110760A (en) * | 2019-04-17 | 2019-08-09 | 浙江工业大学 | A kind of workpiece positioning and recognition methods based on machine vision |
CN110170456A (en) * | 2019-04-30 | 2019-08-27 | 南京邮电大学 | Fruit sorting equipment based on image procossing |
CN110276386A (en) * | 2019-06-11 | 2019-09-24 | 济南大学 | A kind of apple grading method and system based on machine vision |
CN110146516A (en) * | 2019-06-17 | 2019-08-20 | 湖南农业大学 | Fruit sorter based on orthogonal binocular machine vision |
CN110174065A (en) * | 2019-06-17 | 2019-08-27 | 湖南农业大学 | Fruit size lossless detection method based on orthogonal binocular machine vision |
CN110146516B (en) * | 2019-06-17 | 2024-04-02 | 湖南农业大学 | Fruit grading device based on orthogonal binocular machine vision |
CN110298885A (en) * | 2019-06-18 | 2019-10-01 | 仲恺农业工程学院 | A kind of stereoscopic vision recognition methods of Non-smooth surface globoid target and positioning clamping detection device and its application |
CN112241747A (en) * | 2019-07-16 | 2021-01-19 | 顺丰科技有限公司 | Object sorting method, device, sorting equipment and storage medium |
CN110788024A (en) * | 2019-11-13 | 2020-02-14 | 苏州大成有方数据科技有限公司 | Automatic sorting system for intelligent manufacturing and working method thereof |
CN111242057A (en) * | 2020-01-16 | 2020-06-05 | 南京理工大学 | Product sorting system, method, computer device and storage medium |
DE102020209937A1 (en) | 2020-08-06 | 2022-02-10 | Bosch Limited | PROCEDURE FOR COUNTING AND CLASSIFICATION OF PRODUCTS USING COMPUTER VISION |
CN114273240A (en) * | 2020-09-27 | 2022-04-05 | 深圳顺丰泰森控股(集团)有限公司 | Express delivery single piece separation method, device and system and storage medium |
CN112329296A (en) * | 2020-10-28 | 2021-02-05 | 天河超级计算淮海分中心 | Fruit mechanical damage calculation method and device, computer equipment and storage medium |
CN112607100A (en) * | 2020-11-22 | 2021-04-06 | 泰州市华仕达机械制造有限公司 | Compatible fruit conveying and distributing system |
CN113145473A (en) * | 2021-02-20 | 2021-07-23 | 广州大学华软软件学院 | Intelligent fruit sorting system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108491892A (en) | fruit sorting system based on machine vision | |
CN110807355B (en) | Pointer instrument detection and reading identification method based on mobile robot | |
CN104715238B (en) | A kind of pedestrian detection method based on multi-feature fusion | |
CN104134209B (en) | A kind of feature extracting and matching method and system in vision guided navigation | |
CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
CN104112269B (en) | A kind of solar battery laser groove parameter detection method and system based on machine vision | |
CN101813475B (en) | Method for adaptively detecting remote obstacle | |
CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
CN106934813A (en) | A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning | |
CN108596880A (en) | Weld defect feature extraction based on image procossing and welding quality analysis method | |
CN105701476A (en) | Machine vision-based automatic identification system and method for production line products | |
CN108319973A (en) | Citrusfruit detection method on a kind of tree | |
CN107392929B (en) | Intelligent target detection and size measurement method based on human eye vision model | |
CN104077577A (en) | Trademark detection method based on convolutional neural network | |
US8700498B2 (en) | Feature analyzing apparatus for a surface of an object | |
CN110779928B (en) | Defect detection device and method | |
CN106897995A (en) | A kind of parts automatic identifying method towards Automatic manual transmission process | |
CN108765402A (en) | Non-woven fabrics defects detection and sorting technique | |
CN103440035A (en) | Gesture recognition system in three-dimensional space and recognition method thereof | |
Feng et al. | A separating method of adjacent apples based on machine vision and chain code information | |
CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
CN106504262A (en) | A kind of small tiles intelligent locating method of multiple features fusion | |
CN111161295A (en) | Background stripping method for dish image | |
CN109255279A (en) | A kind of method and system of road traffic sign detection identification | |
CN107891012B (en) | Pearl size and circularity sorting device based on equivalent algorithm |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |
|
RJ01 | Rejection of invention patent application after publication |