CN111680738A - Screening device for apple quality detection and detection method thereof - Google Patents
Screening device for apple quality detection and detection method thereof Download PDFInfo
- Publication number
- CN111680738A CN111680738A CN202010494774.XA CN202010494774A CN111680738A CN 111680738 A CN111680738 A CN 111680738A CN 202010494774 A CN202010494774 A CN 202010494774A CN 111680738 A CN111680738 A CN 111680738A
- Authority
- CN
- China
- Prior art keywords
- apple
- screening
- quality
- apples
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Sorting Of Articles (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a screening device for detecting the quality of apples and a detection method thereof, and relates to the technical field of agricultural product detection. The screening system comprises a conveyor belt, a screening box and a cloud server, wherein the screening box and the cloud server are erected above the conveyor belt; the input end of the conveyor belt is provided with a current limiting device; the flow limiting device is used for enabling the apples on the conveyor belt to be sequentially arranged and enter the screening box; a convolutional neural network model is built in the cloud server; the convolutional neural network model can be used for carrying out apple quality grade detection on the uploaded apple image and sending a detection result to the single chip microcomputer; the screening incasement portion has installed a plurality of plectrums, and the plectrum is installed directly over the conveyer belt for dial the apple to the equidirectional not. According to the invention, the quality grades of the apples are detected and classified through the convolutional neural network, and the apples of the same class are subjected to size screening through pixel acquisition on the top view, so that the classification of the quality grades of the apples is realized, the detection cost is reduced, the cost is saved, and the detection efficiency is improved.
Description
Technical Field
The invention belongs to the technical field of agricultural product detection, and particularly relates to a screening device for apple quality detection and a detection method thereof.
Background
China is the first major apple producing country in the world, and the national apple yield reaches 4300 ten thousand tons in 2015. However, most of the apples in China are of lower grade in the international market, the domestic high-grade apple market is monopolized by the apples abroad, the amount of the imported apples in 2015 is increased by 50%, and one of the important reasons is that the graded detection investment of the apples in China is insufficient, the requirements of consumers on the higher and higher quality of the apples are difficult to meet, and the apples are mixed in variety and have poor quality.
To improve apple competitiveness, high quality apples need to be selected from general commodities. The commodity treatment of the apple after delivery has a plurality of steps, grading according to different sizes, maturity and qualities is a key link, and the premise of correct grading is to detect the high level of the external quality of the apple.
At present, the external quality of apples in China is mostly detected by manual treatment, and the traditional quality detection methods usually adopt sampling chemical detection, and most of the methods have the defects of complex analysis process, long time consumption, high detection cost, complex technical conditions, difficulty in realizing real-time monitoring, sample damage and the like. In order to realize the rapid and accurate classification of apples according to the comprehensive quality such as size, color, sugar degree and the like, effectively improve the satisfaction degree of consumers, improve the added value of Chinese apple products, improve the price and profit level of Chinese apple exports and improve the international competitiveness, a new rapid nondestructive detection system for apple quality is urgently needed to be developed.
The near infrared spectrum technology is widely used for measuring the quality grade of agricultural products as a nondestructive testing means, can simultaneously detect a plurality of parameters of the apples, mainly focuses on target local information analysis by utilizing the near infrared spectrum analysis technology, is not suitable for target detection with uneven components, and consumes much time for realizing overall target detection. Therefore, the existing apple quality detection system is difficult to simultaneously detect the external image information and the size information.
Disclosure of Invention
The invention aims to provide a screening device and a screening method for apple quality detection, which are used for detecting and classifying the quality grades of apples through a convolutional neural network, and carrying out size screening on apples of the same class through carrying out pixel acquisition on a top view, so that the problems of complex process, long consumed time, high detection cost and harsh technical conditions of the existing apple quality detection are solved.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a screening device for apple quality detection, which comprises a conveyor belt, a screening box and a cloud server, wherein the screening box is erected above the conveyor belt;
the input end of the conveyor belt is provided with a current limiting device; the flow limiting device is used for enabling the apples on the conveyor belt to sequentially arrange and enter the screening box;
high-definition cameras and light sources are arranged at a plurality of positions in the screening box; the high-definition camera is internally provided with a communication module and used for sending the shot apple image to the cloud server for processing through the communication module; a singlechip is also arranged in the screening box;
a convolutional neural network model is built in the cloud server; the convolutional neural network model can be used for carrying out apple quality grade detection on the uploaded apple image and sending a detection result to the single chip microcomputer; the single chip microcomputer is respectively connected with the light source and the shifting piece;
the screening incasement portion has installed a plurality of plectrums, the plectrum is installed directly over the conveyer belt for dial the apple to equidirectional not.
Further, the cloud server comprises an apple quality grade division module, an image preprocessing module, a convolutional neural network model and a quality grade matching module.
Furthermore, the single chip microcomputer is also connected with a display; the display is fixed on the outer wall of the screening box (2).
A detection method of a screening device for apple quality detection comprises the following steps:
step S1: selecting apples with various quality grades for sample image acquisition, sequentially carrying out class marking on pictures in apple grade ranges according to the precision requirement of apple quality grade detection, and respectively using the pictures as a training sample set and a testing sample set;
step S2: building a convolutional neural network model, training sample set data and testing and adjusting the convolutional neural network model;
step S3: conveying apples to be detected on a conveying belt into a screening box;
step S4: after image shooting preprocessing is carried out on the high-definition camera, the image is transmitted into a trained convolutional neural network model;
step S5: after the classification of the convolutional network model, obtaining which label the picture belongs to, and obtaining the quality grade corresponding to the apple;
step S6: the screening box receives the instruction corresponding to the quality grade of the apple, and the corresponding apple is broadcasted to the corresponding track through the control plectrum of the single chip microcomputer.
Further, in step S1, the image of the apple of each quality grade shot by the high definition camera needs to be preprocessed, and the specific flow of the preprocessing is as follows:
step S11: eliminating apple image noise to obtain a gray level image;
step S12: performing histogram equalization processing on the binary image;
step S13: the contrast enhancement picture.
Further, in step S2, the convolutional neural network model is sequentially composed of an input layer, a convolutional layer, a pooling layer, and an output layer; wherein, the input layer is training data, the convolutional layer is a characteristic extraction layer, and the pooling layer is a calculation layer for secondary extraction after being positioned on the convolutional layer; and the second pooling layer is to perform vectorization on the feature data of the pooling layer after completing the feature extraction of the original data, and then to connect to the classifier, and output the classification result through the output layer.
Further, in step S6, after the quality grades with the same quality are broadcast to the corresponding tracks, the apple size is further selected, and the specific size selecting step is as follows:
step S61: a camera right above the screening box shoots a top view of the apple;
step S62: acquiring the distance between the two farthest pixels in the top view of the apple;
step S63: carrying out binarization processing on the overlook image to obtain a plane projection area of the apple;
step S64: the geometric scale of the apple is calculated by a digital image area and an edge analysis method.
The invention has the following beneficial effects:
(1) according to the method, a convolutional neural network model is built by collecting a large number of apples with quality grades as a training sample set and a testing sample set of the convolutional network model, a screening box is erected on a conveyor belt to identify the apples entering a box body, the result of convolutional neural network identification is fed back to a single chip microcomputer, the single chip microcomputer controls a shifting sheet to transfer the corresponding apples to the corresponding track, classification of the apple quality grades is achieved, detection cost is reduced, cost is saved, and detection efficiency is improved;
(2) according to the invention, the apples of the same quality grade screened by the plectrum are screened for the second time, and the top view of the apples is utilized to collect the distance between the two farthest pixels to calculate the geometric size of the apples, so that the quality grades of the apples are more finely classified, and the detection efficiency is improved.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a screening apparatus for apple quality inspection according to the present invention;
FIG. 2 is a diagram of the steps of a screening method for apple quality inspection;
in the drawings, the components represented by the respective reference numerals are listed below:
the method comprises the following steps of 1-a conveyor belt, 2-a screening box, 3-a cloud server and 4-a current limiting device.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a screening apparatus for apple quality inspection, including a conveyor belt 1, a screening box 2 erected above the conveyor belt, and a cloud server 3;
the input end of the conveyor belt 1 is provided with a current limiting device 4; the flow limiting device 4 is used for enabling the apples on the conveyor belt 1 to be sequentially arranged and enter the screening box 2;
high-definition cameras and light sources are arranged at a plurality of positions in the screening box 2; the high-definition camera is internally provided with a communication module and used for sending the shot apple image to the cloud server for processing through the communication module; a singlechip is also arranged in the screening box 2;
a convolutional neural network model is built in the cloud server; the convolutional neural network model can be used for carrying out apple quality grade detection on the uploaded apple image and sending a detection result to the single chip microcomputer; the singlechip is respectively connected with the light source and the shifting piece;
a plurality of poking pieces are arranged in the screening box 2, are arranged right above the conveyor belt 1 and are used for poking apples in different directions; each poking sheet corresponds to a branch of the conveyor belt, and when the assessment to be detected enters the branch road of the conveyor belt, the single chip microcomputer controls the poking sheets at the branch road to poke the apples to the corresponding branch road.
The cloud server comprises an apple quality grade division module, an image preprocessing module, a convolutional neural network model and a quality grade matching module.
Wherein, the singlechip is also connected with a display; the display is fixed on the outer wall of the screening box 2.
Referring to fig. 2, a method for testing a screening device for apple quality testing includes the following steps:
step S1: selecting apples with various quality grades for sample image acquisition, sequentially carrying out class marking on pictures in apple grade ranges according to the precision requirement of apple quality grade detection, and respectively using the pictures as a training sample set and a testing sample set;
step S2: building a convolutional neural network model, training sample set data and testing and adjusting the convolutional neural network model;
step S3: conveying apples to be detected on a conveying belt into a screening box;
step S4: after image shooting preprocessing is carried out on the high-definition camera, the image is transmitted into a trained convolutional neural network model;
step S5: after the classification of the convolutional network model, obtaining which label the picture belongs to, and obtaining the quality grade corresponding to the apple;
step S6: the screening box receives the instruction corresponding to the quality grade of the apple, and the corresponding apple is broadcasted to the corresponding track through the control plectrum of the single chip microcomputer.
In step S1, the image of the apple of each quality level shot by the high definition camera needs to be preprocessed first, and the specific preprocessing flow is as follows:
step S11: eliminating apple image noise to obtain a gray level image;
step S12: performing histogram equalization processing on the binary image;
step S13: the contrast enhancement picture.
In step S2, the convolutional neural network model is composed of an input layer, a convolutional layer, a pooling layer, and an output layer in sequence; wherein, the input layer is training data, the convolutional layer is a characteristic extraction layer, and the pooling layer is a calculation layer for secondary extraction after being positioned on the convolutional layer; and the second pooling layer is to perform vectorization on the feature data of the pooling layer after completing the feature extraction of the original data, and then to connect to the classifier, and output the classification result through the output layer.
In step S6, after the quality grades with the same quality are broadcast to the corresponding tracks, apple size screening is also required, and the specific size screening steps are as follows:
step S61: a camera right above the screening box shoots a top view of the apple;
step S62: acquiring the distance between the two farthest pixels in the top view of the apple;
step S63: carrying out binarization processing on the overlook image to obtain a plane projection area of the apple;
step S64: calculating the geometric scale of the apple by a digital image area and edge analysis method;
under the condition of the same quality grade, the size of the individual head of the apple is also an important factor influencing the value, so that the apple with the same quality grade screened by the plectrum is screened secondarily, the top view of the apple is utilized, the distance between the two farthest pixels is collected to calculate the geometric size of the apple, the quality grade of the apple is classified more finely, the detection efficiency is improved, and meanwhile, the right of consumers can be met to the greatest extent.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (7)
1. The utility model provides a sieving mechanism for apple quality detects, includes conveyer belt (1), erects screening case (2) and high in the clouds server (3) in the conveyer belt top, its characterized in that:
the input end of the conveyor belt (1) is provided with a current limiting device (4); the flow limiting device (4) is used for enabling the apples on the conveyor belt (1) to be sequentially arranged and enter the screening box (2);
high-definition cameras and light sources are arranged at a plurality of positions in the screening box (2); the high-definition camera is internally provided with a communication module and used for sending the shot apple image to the cloud server for processing through the communication module; a singlechip is also arranged in the screening box (2);
a convolutional neural network model is built in the cloud server; the convolutional neural network model can be used for carrying out apple quality grade detection on the uploaded apple image and sending a detection result to the single chip microcomputer; the single chip microcomputer is respectively connected with the light source and the shifting piece;
the apple picking device is characterized in that a plurality of poking pieces are arranged in the screening box (2), and the poking pieces are arranged right above the conveyor belt (1) and used for poking apples to different directions.
2. The screening device for apple quality detection according to claim 1, wherein the cloud server comprises an apple quality grading module, an image preprocessing module, a convolutional neural network model and a quality grade matching module.
3. The screening device for apple quality detection according to claim 1, wherein the single chip microcomputer is further connected with a display; the display is fixed on the outer wall of the screening box (2).
4. A detection method of a screening device for detecting the quality of apples is characterized by comprising the following steps:
step S1: selecting apples with various quality grades for sample image acquisition, sequentially carrying out class marking on pictures in apple grade ranges according to the precision requirement of apple quality grade detection, and respectively using the pictures as a training sample set and a testing sample set;
step S2: building a convolutional neural network model, training sample set data and testing and adjusting the convolutional neural network model;
step S3: conveying apples to be detected on a conveying belt into a screening box;
step S4: after image shooting preprocessing is carried out on the high-definition camera, the image is transmitted into a trained convolutional neural network model;
step S5: after the classification of the convolutional network model, obtaining which label the picture belongs to, and obtaining the quality grade corresponding to the apple;
step S6: the screening box receives the instruction corresponding to the quality grade of the apple, and the corresponding apple is broadcasted to the corresponding track through the control plectrum of the single chip microcomputer.
5. The method as claimed in claim 4, wherein in step S1, the image of each quality level of apple taken by the high definition camera needs to be preprocessed, and the preprocessing includes:
step S11: eliminating apple image noise to obtain a gray level image;
step S12: performing histogram equalization processing on the binary image;
step S13: the contrast enhancement picture.
6. The screening apparatus and the detection method according to claim 4, wherein in step S2, the convolutional neural network model comprises an input layer, a convolutional layer, a pooling layer, and an output layer; wherein, the input layer is training data, the convolutional layer is a characteristic extraction layer, and the pooling layer is a calculation layer for secondary extraction after being positioned on the convolutional layer; and the second pooling layer is to perform vectorization on the feature data of the pooling layer after completing the feature extraction of the original data, and then to connect to the classifier, and output the classification result through the output layer.
7. The screening device and the method as claimed in claim 4, wherein in the step S6, after the quality grade with the same quality is broadcast to the corresponding track, the screening of apple size is further required, and the specific size screening steps are as follows:
step S61: a camera right above the screening box shoots a top view of the apple;
step S62: acquiring the distance between the two farthest pixels in the top view of the apple;
step S63: carrying out binarization processing on the overlook image to obtain a plane projection area of the apple;
step S64: the geometric scale of the apple is calculated by a digital image area and an edge analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010494774.XA CN111680738A (en) | 2020-06-03 | 2020-06-03 | Screening device for apple quality detection and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010494774.XA CN111680738A (en) | 2020-06-03 | 2020-06-03 | Screening device for apple quality detection and detection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111680738A true CN111680738A (en) | 2020-09-18 |
Family
ID=72434650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010494774.XA Withdrawn CN111680738A (en) | 2020-06-03 | 2020-06-03 | Screening device for apple quality detection and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111680738A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560896A (en) * | 2020-11-19 | 2021-03-26 | 安徽理工大学 | Fruit quality screening and classifying system based on image processing |
| CN112744439A (en) * | 2021-01-15 | 2021-05-04 | 湖南镭目科技有限公司 | Remote scrap steel monitoring system based on deep learning technology |
| CN113624759A (en) * | 2021-08-09 | 2021-11-09 | 西安工程大学 | Apple nondestructive testing method based on machine learning |
-
2020
- 2020-06-03 CN CN202010494774.XA patent/CN111680738A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560896A (en) * | 2020-11-19 | 2021-03-26 | 安徽理工大学 | Fruit quality screening and classifying system based on image processing |
| CN112744439A (en) * | 2021-01-15 | 2021-05-04 | 湖南镭目科技有限公司 | Remote scrap steel monitoring system based on deep learning technology |
| CN113624759A (en) * | 2021-08-09 | 2021-11-09 | 西安工程大学 | Apple nondestructive testing method based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680738A (en) | Screening device for apple quality detection and detection method thereof | |
| CN109598715B (en) | Material granularity online detection method based on machine vision | |
| CN101661004B (en) | Visible detection method of welding quality of circuit board based on support vector machine | |
| WO2023168972A1 (en) | Linear array camera-based copper surface defect detection method and apparatus | |
| CN111784633A (en) | Insulator defect automatic detection algorithm for power inspection video | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN111008641B (en) | Power transmission line tower external force damage detection method based on convolutional neural network | |
| CN107121436B (en) | The Intelligent detecting method and identification device of a kind of silicon material quality | |
| WO2021208423A1 (en) | Display card interface machine testing method based on pca learning | |
| CN106645180A (en) | Method for checking defects of substrate glass, field terminal and server | |
| CN110490842A (en) | A kind of steel strip surface defect detection method based on deep learning | |
| CN105334224B (en) | Automate quality testing cloud platform | |
| CN112893159B (en) | Coal gangue sorting method based on image recognition | |
| CN109142368A (en) | Lithium battery pole slice is crumpled detection method and tab welding detection system | |
| CN112541427B (en) | Identification and material quantity evaluation method for high-quality heavy steel scrap | |
| Puno et al. | Quality Assessment of Mangoes using Convolutional Neural Network | |
| CN114359235A (en) | Wood surface defect detection method based on improved YOLOv5l network | |
| CN112560896A (en) | Fruit quality screening and classifying system based on image processing | |
| CN117055249A (en) | Sampling quality inspection analysis system for liquid crystal display screen assembly processing line | |
| CN114708584A (en) | Big data based cigarette product quality defect prevention and control learning system and method | |
| WO2021208424A1 (en) | Laplacian feature mapping learning-based machine testing method for graphics card interface | |
| CN113487570A (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
| CN110991469B (en) | Fruit soluble solid online detection method and system | |
| CN112858311A (en) | Rice phenotype monitoring system and method based on machine vision technology | |
| CN117252459A (en) | Fruit quality evaluation system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200918 |