CN112730425A - Industrial scene oriented product surface defect automatic identification method - Google Patents
Industrial scene oriented product surface defect automatic identification method Download PDFInfo
- Publication number
- CN112730425A CN112730425A CN202011512109.5A CN202011512109A CN112730425A CN 112730425 A CN112730425 A CN 112730425A CN 202011512109 A CN202011512109 A CN 202011512109A CN 112730425 A CN112730425 A CN 112730425A
- Authority
- CN
- China
- Prior art keywords
- defect
- industrial
- product
- information
- defects
- 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- Withdrawn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
- 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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- 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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- 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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
-
- 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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- 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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an industrial scene-oriented automatic product surface defect identification method, relates to the technical field of software and information, and provides an industrial scene-oriented automatic product surface defect identification method. And (3) modifying a deep learning network structure: based on yolov5 deep learning framework, a network structure is modified, and an algorithm model is trained: based on a large amount of defect sample image data and label data, deep learning model training is carried out, a product surface defect detection model is output, and an industrial camera is integrated: and connecting multiple industrial cameras to multiple production lines, and taking pictures of products by the multiple industrial cameras. The invention improves the performance and effect of the model by improving the yolov5 network structure, utilizes the product surface defect detection model to measure the information of the size, position, orientation and the like of the defect area, improves the detection precision, and in addition, a single machine supports a plurality of industrial cameras, thereby improving the use efficiency of a single machine, simultaneously supporting the identification work on a plurality of production lines and meeting the modern use requirements.
Description
Technical Field
The invention relates to the technical field of software and information, in particular to an automatic product surface defect identification method for industrial scenes.
Background
In the field, there are defect detection methods based on image gray scale and morphology, and also defect identification methods based on image depth learning. The above defect detection method based on image gray scale and morphology and the defect identification method based on image deep learning often have the following problems during identification: 1. the defect detection method based on the image gray scale and the morphology has the defects that only some characteristics with obvious rules can be captured, irregular defects cannot be detected, tiny flaws cannot be found, the stability of the product quality cannot be realized, the enterprise competitiveness cannot be improved, and the accuracy of the defect detection method based on the image gray scale and the morphology is low; 2. the defect identification method based on image deep learning is difficult to deal with scenes with various defect types and rapid detection requirements, cannot support the product defect measurement, positioning and identification work on a plurality of production lines of industrial scenes, and cannot meet the modern use requirements. The method provided by the patent removes the above limitations and widens the applicable scenes.
Disclosure of Invention
The invention mainly aims to provide an industrial scene oriented automatic product surface defect identification method, which can effectively solve the problems in the background technology.
In order to achieve the purpose, the invention adopts the technical scheme that:
an industrial scene-oriented automatic product surface defect identification method comprises the following steps:
step one, reforming a deep learning network structure: reconstructing a network structure based on a yolov5 deep learning framework;
step two, training an algorithm model: carrying out deep learning model training on the modified yolov5 based on a large amount of defect sample image data and label data, and outputting a product surface defect detection model;
step three, integrating the industrial camera: accessing multiple industrial cameras on multiple production lines, photographing products by using the multiple industrial cameras, and acquiring image data;
step four, detecting product defects: detecting the product defects based on the product surface defect detection model obtained in the step two, accurately measuring the information such as the size, the position and the orientation of the defects and identifying the defect types;
step five, storing and managing product defect information: storing the defect information and the defect image, and supporting the subsequent inquiry of a user;
step six, message communication: after the product defects are identified, relevant information needs to be sent to an upper computer.
Preferably, the yolov5 network structure in the first step includes a network depth and a convolution kernel number.
Preferably, in the third step, multiple industrial cameras are connected to a single machine together, and the single machine acquires, analyzes and identifies multiple camera visual images.
Preferably, in the fifth step, the defect information is stored in an SQLite database, the defect image is stored as a jpg file, and the defect is framed by a wire frame.
Preferably, in the sixth step, the upper computer is electrically connected with a mechanical arm, and the upper computer controls the mechanical arm to sort the defective products.
Preferably, the defect information in the fifth step includes a size of the product defect, a position of the product defect, an orientation of the product defect, and a type of the product defect.
Preferably, the SQLite database and the jpg file are both located inside a user management query platform.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, through a yolov5 deep learning framework and the transformation of a network structure, the efficiency and the accuracy of a deep learning model are improved, in the process of defect detection by the application model, the information such as the size, the position and the direction of a defect area is accurately measured, the category information of the defect is identified, the information is used as basic data to support upper-layer business application, the phenomenon that only some characteristics with obvious rules can be captured is avoided, tiny flaws can be found, the stability of product quality is ensured, the enterprise competitiveness is improved, and the accuracy of the identification method is improved.
2. In the invention, a single machine supports multiple industrial cameras, the multiple industrial cameras are deployed on multiple production lines, and multiple photos are collected, so that the use efficiency of the single machine is improved, the identification method can be used for dealing with scenes with various defects and rapid detection requirements, can support the product defect measurement, positioning and identification work on the multiple production lines of industrial scenes, and meets the modern use requirements; and the SQLite database is used for storing and managing the defect data, so that the subsequent inquiry of the defect data by a user is facilitated.
Drawings
FIG. 1 is a flow chart of a method for automatically identifying surface defects of a product oriented to an industrial scene according to the present invention;
FIG. 2 is a typical architecture diagram that can be implemented by the method for automatically identifying surface defects of products oriented to industrial scenes according to the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front", "rear", "both ends", "one end", "the other end", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "connected," and the like are to be construed broadly, such as "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
As shown in fig. 1-2, a method for automatically identifying surface defects of a product facing an industrial scene includes the following steps:
step one, reforming a deep learning network structure: reconstructing a network structure based on a yolov5 deep learning framework;
step two, training an algorithm model: carrying out deep learning model training on the modified yolov5 based on a large amount of defect sample image data and label data, and outputting a product surface defect detection model;
step three, integrating the industrial camera: accessing multiple industrial cameras on multiple production lines, photographing products by using the multiple industrial cameras, and acquiring image data;
step four, detecting product defects: detecting the product defects based on the product surface defect detection model obtained in the step two, accurately measuring the information such as the size, the position and the orientation of the defects and identifying the defect types;
step five, storing and managing product defect information: storing the defect information and the defect image, and supporting the subsequent inquiry of a user;
step six, message communication: after the product defects are identified, relevant information needs to be sent to an upper computer.
In the first step, the yolov5 network structure comprises network depth and the number of convolution kernels, and the network depth and the number of convolution kernels in the yolov5 network structure are learned and modified; in the third step, multiple industrial cameras are jointly connected into a single machine, and the single machine collects, analyzes and identifies the visual images of the multiple cameras, so that the product defect detection requirements of multiple production lines are supported, and the utilization rate of the single machine is improved; step five, storing the defect information in an SQLite database, storing the defect image as a jpg file, and framing the defect by using a wire frame, so that the defect information can be conveniently and quickly inquired; in the sixth step, the upper computer is electrically connected with a mechanical arm, and the upper computer controls the mechanical arm to sort the defective products, so that the sorting operation of the defective products is completed in time; the defect information in the step five comprises the size of the product defect, the position of the product defect, the direction of the product defect and the type of the product defect, so that the accuracy of the identification method is improved; the SQLite database and the jpg file are both located in the user management query platform, and a user queries the defect information through the SQLite database and the jpg file in the user management query platform, so that subsequent query of the user is facilitated.
The invention is a method for automatically identifying surface defects of products facing to industrial scenes, which comprises the steps of firstly reconstructing a network structure based on a yolov5 deep learning framework, carrying out model training based on improved yolov5 to obtain a product surface defect detection model, then deploying a product surface defect detection model and a software system, connecting a plurality of production lines with a plurality of industrial cameras, photographing the products by using the plurality of industrial cameras, collecting image data, connecting the plurality of industrial cameras into a single machine together, collecting, analyzing and identifying visual images of the plurality of cameras by using the single machine, improving the utilization rate of the single machine, then analyzing, processing and identifying the collected images by using the obtained product surface defect detection model, outputting size, position, orientation and type information of defects, and storing the defect information and the defect images, supporting subsequent query of a user, storing defect information in an SQLite database, storing a defect image as a jpg file, framing a defect by using a wire frame, identifying the product defect, sending related defect information to an upper computer, and further sorting the defective product by using an upper computer control mechanical arm; the method is characterized in that a visual image queue is used for caching photos from multiple industrial cameras, a product defect detection platform analyzes and identifies a defect image, outputs information such as size, position, direction and type, and sends the information to a third-party system through a message queue, wherein the third-party system comprises a machine-in position. The machine vision is adopted to replace human eyes to detect the quality of industrial products, so that the technical problems of accuracy, objectivity, repeatability and the like of the human eyes are effectively solved; the labor cost is reduced, and the problem of labor shortage is solved; the detection precision is greatly improved, the detection of tiny flaws is facilitated, the stability of product quality is ensured, and the enterprise competitiveness is improved; workers do not need to stay at the production site, so that safety accidents are reduced; through transforming the deep learning network structure, obtain a high-efficient accurate model, the performance of model training and defect identification has been improved, the precision of discernment has been promoted, the regional size of accurate measurement defect of this identification method, central point and position, and discern the defect type, these information are as basic data, support upper business application, and integrate multichannel industrial camera, promote the utilization ratio of unit, reduce cost, make this identification method can deal with the scene that defect kind is various and the short-term test requires, can support the product defect measurement on many production lines of industrial scene, location and discernment work, satisfy modern user demand.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. An industrial scene-oriented automatic product surface defect identification method is characterized by comprising the following steps: the method is characterized in that: the method comprises the following steps:
step one, reforming a deep learning network structure: reconstructing a network structure based on a yolov5 deep learning framework;
step two, training an algorithm model: carrying out deep learning model training on the modified yolov5 based on a large amount of defect sample image data and label data, and outputting a product surface defect detection model;
step three, integrating the industrial camera: accessing multiple industrial cameras on multiple production lines, photographing products by using the multiple industrial cameras, and acquiring image data;
step four, detecting product defects: detecting the product defects based on the product surface defect detection model obtained in the step two, accurately measuring the information such as the size, the position and the orientation of the defects and identifying the defect types;
step five, storing and managing product defect information: storing the defect information and the defect image, and supporting the subsequent inquiry of a user;
step six, message communication: after the product defects are identified, relevant information needs to be sent to an upper computer.
2. The method for automatically identifying the surface defects of the products oriented to the industrial scene as claimed in claim 1, wherein: the yolov5 network structure in the first step comprises the network depth and the number of convolution kernels.
3. The method for automatically identifying the surface defects of the products oriented to the industrial scene as claimed in claim 1, wherein: and in the third step, multiple paths of industrial cameras are jointly connected into a single machine, and the single machine acquires, analyzes and identifies the visual images of the multiple paths of cameras.
4. The method for automatically identifying the surface defects of the products oriented to the industrial scene as claimed in claim 1, wherein: and fifthly, storing the defect information in an SQLite database, storing the defect image as a jpg file, and framing the defect by using a wire frame.
5. The method for automatically identifying the surface defects of the products oriented to the industrial scene as claimed in claim 1, wherein: and in the sixth step, the upper computer is electrically connected with a mechanical arm, and the upper computer controls the mechanical arm to sort the defective products.
6. The method for automatically identifying the surface defects of the products oriented to the industrial scene as claimed in claim 1, wherein: and the defect information in the fifth step comprises the size of the product defect, the position of the product defect, the direction of the product defect and the type of the product defect.
7. The method for automatically identifying the surface defects of the products oriented to the industrial scene as claimed in claim 4, wherein: and the SQLite database and the jpg file are both positioned in the user management query platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011512109.5A CN112730425A (en) | 2020-12-19 | 2020-12-19 | Industrial scene oriented product surface defect automatic identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011512109.5A CN112730425A (en) | 2020-12-19 | 2020-12-19 | Industrial scene oriented product surface defect automatic identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112730425A true CN112730425A (en) | 2021-04-30 |
Family
ID=75603475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011512109.5A Withdrawn CN112730425A (en) | 2020-12-19 | 2020-12-19 | Industrial scene oriented product surface defect automatic identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112730425A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487570A (en) * | 2021-07-06 | 2021-10-08 | 东北大学 | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model |
| CN114998357A (en) * | 2022-08-08 | 2022-09-02 | 长春摩诺维智能光电科技有限公司 | Industrial detection method, system, terminal and medium based on multi-information analysis |
| CN117030724A (en) * | 2023-10-09 | 2023-11-10 | 诺比侃人工智能科技(成都)股份有限公司 | Multi-mode industrial defect analysis method and system based on deep learning |
-
2020
- 2020-12-19 CN CN202011512109.5A patent/CN112730425A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487570A (en) * | 2021-07-06 | 2021-10-08 | 东北大学 | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model |
| CN113487570B (en) * | 2021-07-06 | 2024-01-30 | 东北大学 | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model |
| CN114998357A (en) * | 2022-08-08 | 2022-09-02 | 长春摩诺维智能光电科技有限公司 | Industrial detection method, system, terminal and medium based on multi-information analysis |
| CN114998357B (en) * | 2022-08-08 | 2022-11-15 | 长春摩诺维智能光电科技有限公司 | Industrial detection method, system, terminal and medium based on multi-information analysis |
| CN117030724A (en) * | 2023-10-09 | 2023-11-10 | 诺比侃人工智能科技(成都)股份有限公司 | Multi-mode industrial defect analysis method and system based on deep learning |
| CN117030724B (en) * | 2023-10-09 | 2023-12-08 | 诺比侃人工智能科技(成都)股份有限公司 | Multi-mode industrial defect analysis method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112730425A (en) | Industrial scene oriented product surface defect automatic identification method | |
| EP2341331B1 (en) | Medicine management system | |
| CN109520436B (en) | Butterfly spring three-dimensional size automatic measurement system based on machine vision and measurement method thereof | |
| TWI669519B (en) | Board defect filtering method and device thereof and computer-readabel recording medium | |
| CN114894642B (en) | Fatigue crack propagation rate testing method and device based on deep learning | |
| CN115439452B (en) | Capacitance product detection and evaluation system based on data analysis | |
| CN113421230A (en) | Vehicle-mounted liquid crystal display light guide plate defect visual detection method based on target detection network | |
| CN112964732A (en) | Spinning cake defect visual detection system and method based on deep learning | |
| CN112432902A (en) | Automatic detection system and method for judging cell number through peripheral blood cell morphology | |
| CN113588653A (en) | System and method for detecting and tracking quality of aluminum anode carbon block | |
| CN114972230A (en) | Method and system for detecting defects of circuit board on production line | |
| CN115937101A (en) | Quality detection method, device, equipment and storage medium | |
| CN110286131A (en) | A kind of textile flaw automatic detection analysis prompt system and method | |
| CN116385331A (en) | Flaw detection method, flaw detection system, electronic equipment and medium | |
| WO2023045038A1 (en) | Cloud-fused product sorting system and method | |
| CN109934297A (en) | A kind of rice species test method based on deep learning convolutional neural networks | |
| CN111768439B (en) | Method, device, electronic equipment and medium for determining experiment scores | |
| CN112200778A (en) | Non-contact multi-cable type parameter measurement method and system | |
| WO2022242631A1 (en) | Surface defect detection model training method, and surface defect detection method and system | |
| CN214151768U (en) | Material management system | |
| CN113155862B (en) | Method for simulating yield of polarizing film coiled material | |
| CN115546108A (en) | Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR | |
| CN109101917A (en) | Mask method, training method, the apparatus and system identified again for pedestrian | |
| CN210377485U (en) | Blade identification conformance OCR detection system | |
| WO2021243724A1 (en) | Image processing method, electronic device, vehicle traveling data recorder, and server |
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 |
Application publication date: 20210430 |
|
| WW01 | Invention patent application withdrawn after publication |