CN112446421A - Silkworm cocoon counting and identifying method based on machine vision - Google Patents
Silkworm cocoon counting and identifying method based on machine vision Download PDFInfo
- Publication number
- CN112446421A CN112446421A CN202011233177.8A CN202011233177A CN112446421A CN 112446421 A CN112446421 A CN 112446421A CN 202011233177 A CN202011233177 A CN 202011233177A CN 112446421 A CN112446421 A CN 112446421A
- Authority
- CN
- China
- Prior art keywords
- silkworm
- cocoon
- counting
- cocoons
- silkworm cocoon
- 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
- 241000255789 Bombyx mori Species 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000004519 manufacturing process Methods 0.000 claims abstract description 9
- 238000011161 development Methods 0.000 claims abstract description 6
- 230000018109 developmental process Effects 0.000 claims abstract description 6
- 230000009466 transformation Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 2
- 238000005286 illumination Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 5
- 239000006227 byproduct Substances 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 abstract description 2
- 239000000463 material Substances 0.000 abstract description 2
- 238000011160 research Methods 0.000 abstract description 2
- 238000012356 Product development Methods 0.000 abstract 1
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 4
- 238000002372 labelling Methods 0.000 description 3
- 238000009395 breeding Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 1
- 238000013398 bayesian method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/38—Creation or generation of source code for implementing user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the field of silkworm cocoon counting and identification, in particular to a silkworm cocoon counting and identification method based on machine vision. At present, silkworm cocoons and byproducts thereof have been widely entered into the lives of people along with the improvement of living standard, and then the accurate segmentation, counting and quality detection of the silkworm cocoons on a production line of the silkworm cocoon byproducts have great demands, which has great influence on the society, economic development and agricultural and sideline product development, the invention researches key technologies in the field of silkworm cocoon counting and identification, and the key technologies can be butted with related enterprises after the project is completed, so that advanced technologies are converted into productivity, and great economic benefits are generated; the invention improves the production identification and use efficiency, reduces manpower and material resources, realizes automatic operation, and avoids the problems of low efficiency, high error rate and the like caused by manual counting.
Description
The technical field is as follows:
the invention relates to the field of silkworm cocoon counting and identification, in particular to a silkworm cocoon counting and identification method based on machine vision.
Background art:
at present, silkworm cocoons and byproducts thereof have been widely entered into lives of people along with the improvement of living standard, and accordingly, the accurate segmentation, counting and quality detection of the silkworm cocoons on a silkworm cocoon byproduct production line have great demands, which has great influence on the society, the economic development and the development of agricultural and sideline products. The quality of produced raw silk is determined mainly by detecting the number of the silkworm cocoons at the end and the cocoon peeling rate of the silkworm cocoons in the production of the raw silk, the existing silk reeling equipment basically adopts an automatic silk reeling machine of a fixed fiber control system, the fineness of the raw silk is automatically controlled according to the specification requirement of the raw silk, but the fineness of the raw silk can be changed due to the temperature and humidity change of a workshop, the different cooking degrees of the silkworm cocoons, the difference between raw silk fineness control mechanisms and other factors in the automatic control process of the fineness of the raw silk; in the silk reeling production process, the production scale is bigger, the silkworm is in the growth process, because the influence of breeding method and breeding environment, the cocoon type that leads to finally forming is different, the cocoon type that forms is various, traditional counting method is through artifical count, because the cocoon type is various, every kind of cocoon figure is also bigger, artifical count not only the step is numerous, consuming time and wasting power, and in artifical counting process, because long-time work, cause visual fatigue easily, lead to counting error, most, the hourglass number condition often takes place, even if just the same person, also there is subjective judgement error.
The invention content is as follows:
the invention aims to solve the existing problems and provides a silkworm cocoon counting and identifying method based on machine vision.
The technical solution of the invention is as follows: a silkworm cocoon counting and identifying method based on machine vision carries out segmentation counting processing through technical means of preprocessing, binaryzation, form transformation, distance transformation and connected domain marking, and is characterized by comprising the following steps:
a: selecting hardware equipment to build a silkworm cocoon image acquisition platform;
b: b, establishing a database which is matched with the silkworm cocoon acquisition platform established in the step A and faces silkworm cocoon counting and identification classification;
c: and B, shooting the silkworm cocoons to be detected through the silkworm cocoon image acquisition platform set up in the step A, and counting and identifying the silkworm cocoons by comparing the obtained pictures with the data stored in the database in the step B.
As a preferred technical solution, the step a includes:
a1: hardware selection, wherein the image acquisition platform hardware equipment comprises a CCD camera, a light source and an objective table;
a2: designing a control interface, including image acquisition, display and storage and camera parameter setting;
a3: and B, setting parameters of the CCD camera in the step A1 according to the image quality of the silkworm cocoons to be obtained and the influence of actual environment illumination, and acquiring in an automatic exposure mode and a higher-resolution mode.
As a preferred technical solution, the step B comprises:
b1: photographing the cocoons in the actual production line by using the CCD camera, collecting images of all types of cocoons, converting the images into a JPG format, and using the images as a basic image data source;
b2, acquiring silkworm cocoon sample images including single-type silkworm cocoons and sample images of multiple-type mixed silkworm cocoons to construct a database;
b3: storing data, creating a test folder, uniformly naming the images of the silkworm cocoons collected in the step B2, and determining the number of classified classes according to the quality and the type of the actual silkworm cocoons;
b4: collecting a characteristic data set of a silkworm cocoon target, sorting the data set to obtain characteristic information of a required data set, and then training by using a classifier to generate a target classifier.
As a preferred technical solution, the step C includes:
c1: photographing and taking images of the silkworm cocoons to be detected;
c2: pretreating and binarizing the silkworm cocoon image collected in the step C1, and performing morphological operation after the binarization operation, so that on one hand, hole filling can be performed, and on the other hand, silkworm cocoons adhered to each other can be primarily separated;
c3: after the step C2, finding the center point of the silkworm cocoon outline, and performing distance transformation and normalization operation to express the pixel distance in the binary image of the step C2 in the form of gray value to obtain a gray map;
c4: converting the gray level map in the step C2 into a binary map again through thresholding binary segmentation, so as to facilitate connected domain marking, and then performing morphological operation to enable the silkworm cocoon outline to be complete;
c5: separating the mutually adhered cocoons into independent individuals, marking and counting connected domains, wherein the number of the connected domains is the number of the cocoons, and finally displaying the number of the cocoons through a Qt control interface;
c6, reading the characteristic values from the database to perform SVM training, determining the optimal parameters of the SVM by a grid search cross-validation method, and generating a support vector machine classifier;
c7: segmenting the original silkworm cocoon image acquired in the processing step C2, extracting color characteristic parameters and space characteristic parameters of each type of silkworm cocoon, and storing all the characteristic parameters in a database;
c8: reading characteristic values from the database to perform SVM training, determining SVM optimal parameters through a grid search cross verification method, and generating a support vector machine classifier;
c9: and (3) performing prediction classification on all pixel points of the silkworm cocoon picture to be detected by using the generated support vector machine classifier, and finally achieving the purpose of identification classification.
As an optimal technical scheme, an internal program of the silkworm cocoon image acquisition platform integrates a development environment through VS2013, and a C + + language and Qt graphical user interface development framework is adopted.
Preferably, in the distance transformation and normalization operation in step C3, the distance transformation first determines the center point of the cocoon outline, and the distance from the cocoon center to the boundary is expressed in the form of gray scale values.
The invention has the beneficial effects that:
the invention researches a key technology in the field of counting and identifying the silkworm cocoons, can be butted with related enterprises after projects are finished, converts an advanced technology into productivity and generates greater economic benefit; the invention improves the production identification and use efficiency, reduces manpower and material resources, realizes automatic operation, and avoids the problems of low efficiency, high error rate and the like caused by manual counting.
Description of the drawings:
FIG. 1 is a flow chart of database establishment according to the present invention;
FIG. 2 is a flow chart of cocoon division and counting according to the present invention;
FIG. 3 is a flow chart of SVM recognition and classification in accordance with the present invention;
the specific implementation mode is as follows:
the present invention will be described in further detail with reference to the accompanying drawings.
The invention provides a silkworm cocoon counting and recognition method based on machine vision, which comprises the steps of building a silkworm cocoon image acquisition platform, establishing a database, a silkworm chrysalis segmentation counting method and an SVM recognition and classification method.
FIG. 1 is a flow chart of database establishment according to the present invention, wherein a CCD camera is used to photograph silkworm cocoons, and images of various silkworm cocoons are collected as basic image data sources; converting the picture format into a jpg format; storing data, creating a test folder, collecting silkworm cocoon images, dividing each type into about 500 pieces according to types, uniformly naming pictures, determining the number of the classified types according to the actual quality type of the silkworm cocoons, and creating a txt document for conveniently labeling the pictures and the corresponding labels, wherein the txt document is used for storing a picture name directory and the corresponding labels and is named as test. Labeling, namely labeling different silkworm cocoons of each type, for example, marking the upper cocoon as 0, marking the double-cocoon in the lower cocoon as 1, marking the mouth cocoon as 2 and the like; therefore, the database can be established and is mainly used for cocoon identification and quality detection classification.
FIG. 2 is a flow chart of silkworm cocoon segmentation and counting according to the present invention, which comprises preprocessing and binarizing an acquired silkworm cocoon image, mainly aiming to convert a three-channel color silkworm cocoon image into a binary image for subsequent segmentation, performing morphological operation after the binarizing operation, on one hand, filling holes, on the other hand, preliminarily separating adhered silkworm cocoons, and on the other hand, determining a contour center point by distance transformation, wherein the distance transformation and normalization mainly solve the problem of silkworm cocoon adhesion, the distance transformation firstly determines the center point of the silkworm cocoon contour, the distance from the silkworm cocoon center to the boundary is expressed in a gray scale value form, then performing normalization operation, compressing a data range, shrinking the silkworm cocoon boundary, and thereby separating the adhered silkworm cocoons, the distance transformation expresses the pixel distance in the binary image in the gray scale value form, so that the obtained image is a gray scale image, the thresholding binary segmentation is to convert the gray level image into a binary image again, to mark connected domains in the aspect of the image, and then to complete the silkworm cocoon outline by morphological operation; separating the mutually adhered cocoons to form independent individuals, marking and counting connected domains, wherein the number of the connected domains is the number of the cocoons, and finally displaying the number of the cocoons through a Qt control interface.
Fig. 3 is a flow chart of SVM recognition and classification of the present invention, wherein the classification performance of the SVM is mainly determined by two parameters, namely, a penalty factor C and a parameter of a kernel function, the penalty factor C is used for adjusting the ratio between the confidence range of the learning machine and the experience risk, so that the generalization capability of the learning machine is the best, the selection is determined by a specific problem, and depending on the amount of noise in the data, the kernel function and the parameter thereof have a great influence on the classification performance, here, the RBF kernel function and the parameter g thereof are used, the parameter determination process of the SVM is an optimization process in essence, and the SVM parameter determination method mainly comprises: experience selection method, experiment trial and error method, gradient descent method, cross verification method, Bayesian method, etc.; the project determines two SVM parameters, a penalty factor C and a parameter g of an RBF kernel function through a grid search cross verification method, most of identification classification is composed of a training process and an identification process, in the training process, a characteristic data set corresponding to a target is collected firstly, the data set is sorted to obtain characteristic information of the required data set, and then a classifier is used for training to generate a target classifier; in the identification process, the characteristic information and the classifier obtained in the training process are utilized, and the target meeting the judgment of the classifier as positive is searched out by comparing the scanning window with the input image.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the principles of the invention, and these modifications and variations also fall within the scope of the invention as defined in the appended claims.
Claims (6)
1. A silkworm cocoon counting and identifying method based on machine vision carries out segmentation counting processing through technical means of preprocessing, binaryzation, form transformation, distance transformation and connected domain marking, and is characterized by comprising the following steps:
a: selecting hardware equipment to build a silkworm cocoon image acquisition platform;
b: b, establishing a database which is matched with the silkworm cocoon acquisition platform established in the step A and faces silkworm cocoon counting and identification classification;
c: and B, shooting the silkworm cocoons to be detected through the silkworm cocoon image acquisition platform set up in the step A, and counting and identifying the silkworm cocoons by comparing the obtained pictures with the data stored in the database in the step B.
2. A machine vision based cocoon counting and recognition method according to claim 1, characterized in that said step a comprises:
a1: hardware selection, wherein the image acquisition platform hardware equipment comprises a CCD camera, a light source and an objective table;
a2: designing a control interface, including image acquisition, display and storage and camera parameter setting;
a3: and B, setting parameters of the CCD camera in the step A1 according to the image quality of the silkworm cocoons to be obtained and the influence of actual environment illumination, and acquiring in an automatic exposure mode and a higher-resolution mode.
3. A machine vision based cocoon counting and recognition method according to claim 1, wherein the step B comprises:
b1: photographing the cocoons in the actual production line by using the CCD camera, collecting images of all types of cocoons, converting the images into a JPG format, and using the images as a basic image data source;
b2, acquiring silkworm cocoon sample images including single-type silkworm cocoons and sample images of multiple-type mixed silkworm cocoons to construct a database;
b3: storing data, creating a test folder, uniformly naming the images of the silkworm cocoons collected in the step B2, and determining the number of classified classes according to the quality and the type of the actual silkworm cocoons;
b4: collecting a characteristic data set of a silkworm cocoon target, sorting the data set to obtain characteristic information of a required data set, and then training by using a classifier to generate a target classifier.
4. A machine vision based cocoon counting and recognition method as claimed in claim 1, wherein said step C comprises:
c1: photographing and taking images of the silkworm cocoons to be detected;
c2: pretreating and binarizing the silkworm cocoon image collected in the step C1, and performing morphological operation after the binarization operation, so that on one hand, hole filling can be performed, and on the other hand, silkworm cocoons adhered to each other can be primarily separated;
c3: after the step C2, finding the center point of the silkworm cocoon outline, and performing distance transformation and normalization operation to express the pixel distance in the binary image of the step C2 in the form of gray value to obtain a gray map;
c4: converting the gray level map in the step C2 into a binary map again through thresholding binary segmentation, so as to facilitate connected domain marking, and then performing morphological operation to enable the silkworm cocoon outline to be complete;
c5: separating the mutually adhered cocoons into independent individuals, marking and counting connected domains, wherein the number of the connected domains is the number of the cocoons, and finally displaying the number of the cocoons through a Qt control interface;
c6, reading the characteristic values from the database to perform SVM training, determining the optimal parameters of the SVM by a grid search cross-validation method, and generating a support vector machine classifier;
c7: segmenting the original silkworm cocoon image acquired in the processing step C2, extracting color characteristic parameters and space characteristic parameters of each type of silkworm cocoon, and storing all the characteristic parameters in a database;
c8: reading characteristic values from the database to perform SVM training, determining SVM optimal parameters through a grid search cross verification method, and generating a support vector machine classifier;
c9: and (3) performing prediction classification on all pixel points of the silkworm cocoon picture to be detected by using the generated support vector machine classifier, and finally achieving the purpose of identification classification.
5. A machine vision based cocoon counting and recognition method as claimed in claim 1, wherein: and integrating a development environment by an internal program of the silkworm cocoon image acquisition platform through VS2013, and developing a framework by adopting a C + + language and a Qt graphical user interface.
6. A machine vision based cocoon counting and recognition method as claimed in claim 3, wherein: in the distance transformation and normalization operation in the step C3, the distance transformation first determines the center point of the cocoon outline, and the distance from the cocoon center to the boundary is expressed in the form of gray value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011233177.8A CN112446421A (en) | 2020-11-06 | 2020-11-06 | Silkworm cocoon counting and identifying method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011233177.8A CN112446421A (en) | 2020-11-06 | 2020-11-06 | Silkworm cocoon counting and identifying method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112446421A true CN112446421A (en) | 2021-03-05 |
Family
ID=74736209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011233177.8A Pending CN112446421A (en) | 2020-11-06 | 2020-11-06 | Silkworm cocoon counting and identifying method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446421A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269275A (en) * | 2021-06-21 | 2021-08-17 | 昆明理工大学 | Real-time detection method for silkworm cocoon |
| CN115294167A (en) * | 2022-10-08 | 2022-11-04 | 维柏思特衬布（南通）有限公司 | Data processing-based silkworm cocoon number identification method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246920A (en) * | 2013-03-22 | 2013-08-14 | 浙江理工大学 | Automatic counting method and system for silkworm cocoons |
| CN106198448A (en) * | 2016-07-17 | 2016-12-07 | 北京化工大学 | A kind of automatic high speed lossless sorting live body male and female Pupa bombycis or the technique of live body male and female Bombyx bombycis |
| CN108596891A (en) * | 2018-04-23 | 2018-09-28 | 中国计量大学 | A kind of method of counting towards multiple types mixing silk cocoon |
| CN109409440A (en) * | 2018-11-09 | 2019-03-01 | 中国计量大学 | A kind of silk cocoon classification method based on color characteristic and support vector machines |
| CN209215218U (en) * | 2018-09-29 | 2019-08-06 | 王玮琳 | A kind of silk cocoon detection device |
| CN210924657U (en) * | 2019-05-13 | 2020-07-03 | 中国计量大学 | Multiple type of silkworm cocoon counting assembly based on machine vision |
-
2020
- 2020-11-06 CN CN202011233177.8A patent/CN112446421A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246920A (en) * | 2013-03-22 | 2013-08-14 | 浙江理工大学 | Automatic counting method and system for silkworm cocoons |
| CN106198448A (en) * | 2016-07-17 | 2016-12-07 | 北京化工大学 | A kind of automatic high speed lossless sorting live body male and female Pupa bombycis or the technique of live body male and female Bombyx bombycis |
| CN108596891A (en) * | 2018-04-23 | 2018-09-28 | 中国计量大学 | A kind of method of counting towards multiple types mixing silk cocoon |
| CN209215218U (en) * | 2018-09-29 | 2019-08-06 | 王玮琳 | A kind of silk cocoon detection device |
| CN109409440A (en) * | 2018-11-09 | 2019-03-01 | 中国计量大学 | A kind of silk cocoon classification method based on color characteristic and support vector machines |
| CN210924657U (en) * | 2019-05-13 | 2020-07-03 | 中国计量大学 | Multiple type of silkworm cocoon counting assembly based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| ALEX NOEL JOSEPH RAJ ET AL.: "A Multi-Sensor System for Silkworm Cocoon Gender Classification via Image Processing and Support Vector Machine", 《SENSORS》, 31 December 2019 (2019-12-31), pages 1 - 18 * |
| 孙卫红 等: "基于颜色特征和支持向量机的蚕茧分类方法研究", 《蚕业科学》, vol. 46, no. 1, 29 February 2020 (2020-02-29), pages 86 - 95 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269275A (en) * | 2021-06-21 | 2021-08-17 | 昆明理工大学 | Real-time detection method for silkworm cocoon |
| CN113269275B (en) * | 2021-06-21 | 2023-06-06 | 昆明理工大学 | Real-time detection method for cocoons under cocoons |
| CN115294167A (en) * | 2022-10-08 | 2022-11-04 | 维柏思特衬布（南通）有限公司 | Data processing-based silkworm cocoon number identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101873135B1 (en) | Fluoroscopic examination system and method capable of conducting automatic classification and recognition on goods | |
| CN103518224B (en) | Method for analysing microbial growth | |
| CN107944504B (en) | Board recognition and machine learning method and device for board recognition and electronic equipment | |
| CN109684906B (en) | Method for detecting red fat bark beetles based on deep learning | |
| CN1162798C (en) | Chinese medicine tongue colour, fur colour and tongue fur thickness analysis method based on multiclass support vector machine | |
| CN112446421A (en) | Silkworm cocoon counting and identifying method based on machine vision | |
| CN112580748B (en) | Method for counting classified cells of stain image | |
| WO2016189469A1 (en) | A method for medical screening and a system therefor | |
| CN108537751A (en) | A kind of Thyroid ultrasound image automatic segmentation method based on radial base neural net | |
| CN109948429A (en) | Image analysis method, device, electronic equipment and computer-readable medium | |
| CN111681220B (en) | Method, device, system and storage medium for constructing defect detection model | |
| CN111079511A (en) | Document automatic classification and optical character recognition method and system based on deep learning | |
| CN111062260A (en) | Automatic generation method of facial cosmetic recommendation scheme | |
| CN107578067A (en) | A kind of recognition methods of pipe tobacco component and device based on convolutional neural networks | |
| CN111899214B (en) | Pathological section scanning analysis device and pathological section scanning method | |
| CN107563327B (en) | Pedestrian re-identification method and system based on self-walking feedback | |
| CN110210401B (en) | Intelligent target detection method under weak light | |
| CN115601747A (en) | Method and system for calculating confluency of adherent cells | |
| CN113869124A (en) | Deep learning-based blood cell morphology classification method and system | |
| CN113221930A (en) | Image processing method based on deep learning | |
| EP3973476A1 (en) | Systems and methods to train a cell object detector | |
| WO2020120039A1 (en) | Classification of cell nuclei | |
| CN115309941B (en) | AI-based intelligent tag retrieval method and system | |
| CN108664617A (en) | Quick marketing method of servicing based on image recognition and retrieval | |
| CN109919924A (en) | A method of suitable for high-volume HE dyeing picture cell number wordization processing |
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 |