CN111462043B - Defect detection method, device, equipment and medium based on Internet - Google Patents
Defect detection method, device, equipment and medium based on Internet Download PDFInfo
- Publication number
- CN111462043B CN111462043B CN202010146331.1A CN202010146331A CN111462043B CN 111462043 B CN111462043 B CN 111462043B CN 202010146331 A CN202010146331 A CN 202010146331A CN 111462043 B CN111462043 B CN 111462043B
- Authority
- CN
- China
- Prior art keywords
- file
- image
- training
- defect
- deep neural
- 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.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 86
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 90
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004806 packaging method and process Methods 0.000 claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims description 43
- 238000002372 labelling Methods 0.000 claims description 39
- 230000006835 compression Effects 0.000 claims description 16
- 238000007906 compression Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 abstract description 10
- 238000004519 manufacturing process Methods 0.000 abstract description 9
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012856 packing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Abstract
The application provides a defect detection method, device, equipment and medium based on Internet, the method includes the steps of S1, reading image files, marking defect targets in the image files, packaging marked image file data and transmitting the marked image file data to a network server; s2, receiving a training weight file returned by the network server after the deep neural network training is performed based on the image file data; and S3, loading the training weight file by using an inference tool to infer the image file, so as to obtain the coordinate position and the category information of the image file. The application has the advantages that: the method can realize quick updating to obtain a better training weight model, achieve a better detection effect and further greatly improve the production efficiency.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for detecting defects based on an Internet network.
Background
The surface defect detection of industrial products is an important link in the industrial production process, and the defects of the products and the process can be conveniently and timely found through the defect detection, so that the quality of the products is controlled. At present, a surface defect detection technology based on machine vision is widely applied to various links of industrial production, and plays an important role in improving production efficiency and ensuring product quality in automatic production.
The surface defect detection based on machine vision comprises two main steps, namely firstly, high-definition imaging is carried out on a product to ensure that the product defect can be displayed on an image, and secondly, analysis processing is carried out on the image from imaging equipment to tell a user which place in the image has the defect, and the type, the position information and the like of the defect. Surface defect detection based on the traditional image processing and machine learning methods still has many problems, such as frequent parameter adjustment required by an algorithm, failure of precision to meet the requirements of clients, poor detection stability and the like, although the development has been carried out for many years. The deep neural network model is a revolutionary machine learning method and technology, has excellent performances in various fields, such as face recognition, object classification and the like, and is expected to solve the problem of industrial surface defect detection.
In recent years, deep learning techniques have been primarily applied to industrial surface defect detection, but the speed and accuracy are quite long from the true solution. The main reasons are: on the one hand, the technical scheme is too single, for example, a single complex model is designed to classify a rectangular area with a fixed size in an input image, and whether the area has defects is judged; on the other hand, the design of the technical scheme does not deeply combine the actual conditions of industrial production, so that the technical scheme is difficult to land. The main problems presented are: the marking and training period is long, the detection speed is low, and the production efficiency is low.
Disclosure of Invention
The application aims to solve the technical problems of long labeling and training period, low detection speed and low production efficiency of the existing industrial surface defect detection.
In a first aspect, the present application provides a defect detection method based on an Internet network, where the method is applied to a terminal, and the detection method includes:
s1, reading an image file, marking a defect target in the image file, and packaging and transmitting marked image file data to a network server;
s2, receiving a training weight file returned by the network server after the deep neural network training is performed based on the image file data;
and S3, loading the training weight file by using an inference tool to infer the image file, so as to obtain the coordinate position and the category information of the image file.
Further, the step S1 specifically includes:
reading image files from an image folder, drawing out an ROI (region of interest) of a defect target in the image file by using polygons for each read image file, acquiring coordinate information of the ROI, setting a class name and a class serial number of the defect target, and storing the coordinate information, the class name and the class serial number into a defect labeling file; placing the defect labeling file and the image file into a new folder, and packaging and transmitting the whole new folder to a network server by using a compression tool;
and simultaneously, acquiring a deep neural network model file, and transmitting the deep neural network model file to a network server.
Further, in the step S2, the training weight file returned by the network server after performing the deep neural network training based on the image file data is specifically:
decompressing the received compressed package of the new folder by the network server, and acquiring a defect labeling file and an image file from the new folder into a memory; simultaneously, reading file information of the deep neural network model file into a memory; and reading the defect labeling file and the image file by using a training tool, training the deep neural network model file to obtain a training weight file, packaging the training weight file by using a compression tool, and returning the training weight file to the terminal.
Further, the network server is a GPU cloud server, an AI cloud server, a lan GPU server or a lan AI server.
Further, the training tool is a tensorflow tool or a pyrach tool; the deep neural network model file is a fast-RCNN model file.
In a second aspect, the application provides a defect detection device based on an Internet network, wherein the detection device comprises an image labeling module, a weight file receiving module and an image reasoning module;
the image labeling module is used for reading an image file, labeling a defect target in the image file, and packaging and transmitting labeled image file data to the network server;
the weight file receiving module is used for receiving training weight files returned by the network server after the deep neural network training is performed based on the image file data;
the image reasoning module is used for loading the training weight file by using the reasoning tool to reason the image file, so as to obtain the coordinate position and the category information of the image file.
Further, the image labeling module specifically comprises: reading image files from an image folder, drawing out an ROI (region of interest) of a defect target in the image file by using polygons for each read image file, acquiring coordinate information of the ROI, setting a class name and a class serial number of the defect target, and storing the coordinate information, the class name and the class serial number into a defect labeling file; placing the defect labeling file and the image file into a new folder, and packaging and transmitting the whole new folder to a network server by using a compression tool;
and simultaneously, acquiring a deep neural network model file, and transmitting the deep neural network model file to a network server.
Further, in the weight file receiving module, the training weight file returned by the network server after the deep neural network training based on the image file data is specifically:
decompressing the received compressed package of the new folder by the network server, and acquiring a defect labeling file and an image file from the new folder into a memory; simultaneously, reading file information of the deep neural network model file into a memory; and reading the defect labeling file and the image file by using a training tool, training the deep neural network model file to obtain a training weight file, packaging the training weight file by using a compression tool, and returning the training weight file to the terminal.
In a third aspect, the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method of the first aspect.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
when the technical scheme is implemented in practice, the method and the device can be very convenient for professional technicians to quickly and accurately label the image files on the terminal and generate the defect labeling files, so that the problem of undefined defect judgment standards can be effectively avoided; after the labeling is completed, the terminal packages the labeled image file data and transmits the packaged image file data to the network server for training, so that the problem of long labeling and training period can be effectively solved; finally, the trained training weight file is returned to the terminal for reasoning, so that the better training weight model can be obtained by quick updating, a better detection effect is achieved, and further the production efficiency is greatly improved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
The application will be further described with reference to examples of embodiments with reference to the accompanying drawings.
FIG. 1 is a flowchart illustrating a defect detection method based on the Internet according to a first embodiment of the present application;
FIG. 2 is a schematic diagram of a defect detecting device based on Internet network in a second embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of a medium in a fourth embodiment of the present application.
Detailed Description
The embodiment of the application provides a defect detection method, device, equipment and medium based on an Internet network, which are used for solving the problems of low production efficiency caused by long marking and training period and low detection speed in the existing industrial surface defect detection.
The technical scheme in the embodiment of the application has the following overall thought: after marking the defect target in the image file through the terminal, packaging the marked image file data and transmitting the packaged image file data to the network server; after the network server performs deep neural network training on the image file data, returning the obtained training weight file to the terminal; and the terminal loads the training weight file to infer the image file, so as to obtain the coordinate position and the category information of the image file.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
Example 1
The present embodiment provides a defect detection method based on an Internet network, as shown in fig. 1, where the method is applied to a terminal, and the terminal may, but is not limited to, a PC, a mobile phone, a small workstation, etc., and the detection method includes:
s1, reading an image file, marking a defect target in the image file, and packaging and transmitting marked image file data to a network server; the network server is a GPU cloud server, an AI cloud server, a local area network GPU server or a local area network AI server;
s2, receiving a training weight file returned by the network server after the deep neural network training is performed based on the image file data;
and S3, loading the training weight file by using an inference tool to infer the image file, so as to obtain the coordinate position and the category information of the image file. In the implementation of the application, the training weight file can be loaded by using an inference tool index. Py in a tensorflow tool to infer the image file, so that the coordinate position and the category information of the image file can be obtained, such as the coordinates, the category name information, the category serial number information and the like of 4 vertexes of the defect target rectangular frame can be obtained.
In this embodiment, the step S1 specifically includes:
reading image files from an image folder, if the image folder contains a plurality of image files, sequentially reading the image files from the image folder, marking the read image files, drawing out the ROI (region of interest) of a defect target in the image file by using polygons for each read image file, acquiring coordinate information of the ROI, setting a category name and a category sequence number of the defect target, and storing the coordinate information, the category name and the category sequence number into a defect marking file, wherein the defect marking file can be a txt text file; placing the defect labeling file and the image file into a new folder, and packing and transmitting the whole new folder to a network server by using a compression tool, wherein the compression tool can adopt 7zip, can adopt an http mode for transmission when transmitting a compression packet, and can also adopt other modes such as ftp and the like for transmission; the polygon is preferably rectangular, and of course, other polygons can be adopted for marking, so long as the defect target can be surrounded; the coordinate information includes coordinates of the respective vertices of the ROI area, for example, if a rectangle is drawn, the coordinate information includes coordinates of 4 vertices of the rectangle; the class names and the class serial numbers can be defined by themselves according to the needs, the class names are mainly used for representing the names of defects, and the class serial numbers are mainly used for representing the defects;
meanwhile, a deep neural network model file is obtained, and the deep neural network model file is a fast-RCNN model file, and of course, other deep neural network model files can be adopted according to actual needs to transmit the deep neural network model file to a network server, and the deep neural network model file can be transmitted in an http mode or in other modes such as ftp mode when transmitted. The deep neural network model file is a pre-trained weight file, and in practice, the deep neural network model file may be directly downloaded from the network, such as: the received ionv3_fp32_pre-transmitted_model.
In this embodiment, in the step S2, the training weight file returned by the network server after performing the deep neural network training based on the image file data is specifically:
decompressing the received compressed package of the new folder by the network server, and acquiring a defect labeling file and an image file from the new folder into a memory; simultaneously, reading file information of the deep neural network model file into a memory; and reading the defect labeling file and the image file by using a training tool, training the deep neural network model file to obtain a training weight file, packaging the training weight file by using a compression tool, and returning the training weight file to the terminal. The training tool is a tensorflow tool or a pyrach tool, and other training tools can be selected according to actual needs; in the implementation, for example, the train. Py of the tensorflow tool can be used for reading the defect labeling file and the image file to train the deep neural network model file, and a training weight file and a file with the suffix name pb can be obtained after training is completed; the training weight file after training contains various training configuration parameters, such as learning rate, threshold value, structural data of the deep neural network model and the like.
Based on the same inventive concept, the application also provides a device corresponding to the method in the first embodiment, and the details of the second embodiment are shown.
Example two
In this embodiment, an Internet network-based defect detection device is provided, as shown in fig. 2, where the detection device includes an image labeling module, a weight file receiving module, and an image reasoning module;
the image labeling module is used for reading an image file, labeling a defect target in the image file, and packaging and transmitting labeled image file data to the network server; the network server is a GPU cloud server, an AI cloud server, a local area network GPU server or a local area network AI server;
the weight file receiving module is used for receiving training weight files returned by the network server after the deep neural network training is performed based on the image file data;
the image reasoning module is used for loading the training weight file by using the reasoning tool to reason the image file, so as to obtain the coordinate position and the category information of the image file. In the implementation of the application, the training weight file can be loaded by using an inference tool index. Py in a tensorflow tool to infer the image file, so that the coordinate position and the category information of the image file can be obtained, such as the coordinates, the category name information, the category serial number information and the like of 4 vertexes of the defect target rectangular frame can be obtained.
In this embodiment, the image labeling module specifically includes:
reading image files from an image folder, if the image folder contains a plurality of image files, sequentially reading the image files from the image folder, marking the read image files, drawing out the ROI (region of interest) of a defect target in the image file by using polygons for each read image file, acquiring coordinate information of the ROI, setting a category name and a category sequence number of the defect target, and storing the coordinate information, the category name and the category sequence number into a defect marking file, wherein the defect marking file can be a txt text file; placing the defect labeling file and the image file into a new folder, and packing and transmitting the whole new folder to a network server by using a compression tool, wherein the compression tool can adopt 7zip, can adopt an http mode for transmission when transmitting a compression packet, and can also adopt other modes such as ftp and the like for transmission; the polygon is preferably rectangular, and of course, other polygons can be adopted for marking, so long as the defect target can be surrounded; the coordinate information includes coordinates of the respective vertices of the ROI area, for example, if a rectangle is drawn, the coordinate information includes coordinates of 4 vertices of the rectangle; the class names and the class serial numbers can be defined by themselves according to the needs, the class names are mainly used for representing the names of defects, and the class serial numbers are mainly used for representing the defects;
meanwhile, a deep neural network model file is obtained, and the deep neural network model file is a fast-RCNN model file, and of course, other deep neural network model files can be adopted according to actual needs to transmit the deep neural network model file to a network server, and the deep neural network model file can be transmitted in an http mode or in other modes such as ftp mode when transmitted. The deep neural network model file is a pre-trained weight file, and in practice, the deep neural network model file may be directly downloaded from the network, such as: the received ionv3_fp32_pre-transmitted_model.
In this embodiment, in the weight file receiving module, the training weight file returned by the network server after performing the deep neural network training based on the image file data is specifically:
decompressing the received compressed package of the new folder by the network server, and acquiring a defect labeling file and an image file from the new folder into a memory; simultaneously, reading file information of the deep neural network model file into a memory; and reading the defect labeling file and the image file by using a training tool, training the deep neural network model file to obtain a training weight file, packaging the training weight file by using a compression tool, and returning the training weight file to the terminal. The training tool is a tensorflow tool or a pyrach tool, and other training tools can be selected according to actual needs; in the implementation, for example, the train. Py of the tensorflow tool can be used for reading the defect labeling file and the image file to train the deep neural network model file, and a training weight file and a file with the suffix name pb can be obtained after training is completed; the training weight file after training contains various training configuration parameters, such as learning rate, threshold value, structural data of the deep neural network model and the like.
Since the device described in the second embodiment of the present application is a device for implementing the method described in the first embodiment of the present application, based on the method described in the first embodiment of the present application, a person skilled in the art can understand the specific structure and the deformation of the device, and thus the detailed description thereof is omitted herein. All devices used in the method according to the first embodiment of the present application are within the scope of the present application.
Based on the same inventive concept, the application provides an electronic device embodiment corresponding to the first embodiment, and the details of the third embodiment are shown in the specification.
Example III
The present embodiment provides an electronic device, as shown in fig. 3, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where any implementation of the first embodiment may be implemented when the processor executes the computer program.
Since the electronic device described in this embodiment is a device for implementing the method in the first embodiment of the present application, those skilled in the art will be able to understand the specific implementation of the electronic device and various modifications thereof based on the method described in the first embodiment of the present application, so how the electronic device implements the method in the embodiment of the present application will not be described in detail herein. The apparatus used to implement the methods of embodiments of the present application will be within the scope of the intended protection of the present application.
Based on the same inventive concept, the application provides a storage medium corresponding to the first embodiment, and the detail of the fourth embodiment is shown in the specification.
Example IV
The present embodiment provides a computer readable storage medium, as shown in fig. 4, on which a computer program is stored, which when executed by a processor, can implement any implementation of the first embodiment.
It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The technical scheme provided by the embodiment of the application has at least the following technical effects or advantages: when the technical scheme is implemented in practice, the method and the device can be very convenient for professional technicians to quickly and accurately label the image files on the terminal and generate the defect labeling files, so that the problem of undefined defect judgment standards can be effectively avoided; after the labeling is completed, the terminal packages the labeled image file data and transmits the packaged image file data to the network server for training, so that the problem of long labeling and training period can be effectively solved; finally, the trained training weight file is returned to the terminal for reasoning, so that the better training weight model can be obtained by quick updating, a better detection effect is achieved, and further the production efficiency is greatly improved.
While specific embodiments of the application have been described above, it will be appreciated by those skilled in the art that the specific embodiments described are illustrative only and not intended to limit the scope of the application, and that equivalent modifications and variations of the application in light of the spirit of the application will be covered by the claims of the present application.
Claims (5)
1. A defect detection method based on Internet network is characterized in that: the method is applied to the terminal, and the detection method comprises the following steps:
s1, reading image files from an image folder, drawing out a ROI (region of interest) of a defect target in the image file by using polygons for each read image file, acquiring coordinate information of the ROI, setting a category name and a category serial number of the defect target, and storing the coordinate information, the category name and the category serial number into a defect labeling file; placing the defect labeling file and the image file into a new folder, and packaging and transmitting the whole new folder to a network server by using a compression tool; the network server is a GPU cloud server, an AI cloud server, a local area network GPU server or a local area network AI server;
meanwhile, a deep neural network model file is obtained, and the deep neural network model file is transmitted to a network server;
step S2, decompressing the received compressed package of the new folder by the network server, and acquiring a defect labeling file and an image file from the new folder into a memory; simultaneously, reading file information of the deep neural network model file into a memory; reading the defect labeling file and the image file by using a training tool, training the deep neural network model file to obtain a training weight file, packaging the training weight file by using a compression tool, and returning the training weight file to the terminal; the training weight file at least comprises the learning rate, a threshold value and structural data of a deep neural network model;
and S3, loading the training weight file by using an inference tool to infer the image file, so as to obtain the coordinate position and the category information of the image file.
2. The defect detection method based on the Internet network according to claim 1, wherein: the training tool is a tensorlow tool or a pyrach tool; the deep neural network model file is a fast-RCNN model file.
3. The defect detection device based on the Internet network is characterized in that: the detection device comprises an image annotation module, a weight file receiving module and an image reasoning module;
the image labeling module is used for reading image files from the image folder, drawing out the ROI (region of interest) of the defect target in the image file by using polygons for each read image file, acquiring coordinate information of the ROI, setting a category name and a category serial number of the defect target, and storing the coordinate information, the category name and the category serial number into the defect labeling file; placing the defect labeling file and the image file into a new folder, and packaging and transmitting the whole new folder to a network server by using a compression tool; the network server is a GPU cloud server, an AI cloud server, a local area network GPU server or a local area network AI server;
meanwhile, a deep neural network model file is obtained, and the deep neural network model file is transmitted to a network server;
the weight file receiving module is used for decompressing the received compressed package of the new folder by the network server, and acquiring a defect marking file and an image file from the new folder into the memory; simultaneously, reading file information of the deep neural network model file into a memory; reading the defect labeling file and the image file by using a training tool, training the deep neural network model file to obtain a training weight file, packaging the training weight file by using a compression tool, and returning the training weight file to the terminal; the training weight file at least comprises the learning rate, a threshold value and structural data of a deep neural network model;
the image reasoning module is used for loading the training weight file by using the reasoning tool to reason the image file, so as to obtain the coordinate position and the category information of the image file.
4. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 2 when the program is executed by the processor.
5. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010146331.1A CN111462043B (en) | 2020-03-05 | 2020-03-05 | Defect detection method, device, equipment and medium based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010146331.1A CN111462043B (en) | 2020-03-05 | 2020-03-05 | Defect detection method, device, equipment and medium based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111462043A CN111462043A (en) | 2020-07-28 |
| CN111462043B true CN111462043B (en) | 2023-10-24 |
Family
ID=71684968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010146331.1A Active CN111462043B (en) | 2020-03-05 | 2020-03-05 | Defect detection method, device, equipment and medium based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111462043B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320278A (en) * | 2018-01-09 | 2018-07-24 | 北京百度网讯科技有限公司 | Product defects detect localization method, device, equipment and computer-readable medium |
| CN109859207A (en) * | 2019-03-06 | 2019-06-07 | 华南理工大学 | A kind of defect inspection method of high density flexible substrate |
| CN110554047A (en) * | 2019-09-06 | 2019-12-10 | 腾讯科技（深圳）有限公司 | method, device, system and equipment for processing product defect detection data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776808A (en) * | 2018-05-25 | 2018-11-09 | 北京百度网讯科技有限公司 | A kind of method and apparatus for detecting ladle corrosion defect |
-
2020
- 2020-03-05 CN CN202010146331.1A patent/CN111462043B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320278A (en) * | 2018-01-09 | 2018-07-24 | 北京百度网讯科技有限公司 | Product defects detect localization method, device, equipment and computer-readable medium |
| CN109859207A (en) * | 2019-03-06 | 2019-06-07 | 华南理工大学 | A kind of defect inspection method of high density flexible substrate |
| CN110554047A (en) * | 2019-09-06 | 2019-12-10 | 腾讯科技（深圳）有限公司 | method, device, system and equipment for processing product defect detection data |
Non-Patent Citations (1)
| Title |
|---|
| Faster R-CNN在工业CT图像缺陷检测中的应用;常海涛等;《中国图象图形学报》;20180716(第07期);第129-139页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111462043A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108656107B (en) | Mechanical arm grabbing system and method based on image processing | |
| WO2021113408A1 (en) | Synthesizing images from 3d models | |
| CN109949693B (en) | Map drawing method and device, computing equipment and storage medium | |
| CN108765584A (en) | Laser point cloud data collection augmentation method, apparatus and readable storage medium storing program for executing | |
| CN110597937B (en) | Unmanned intelligent inspection method, device, equipment and storage medium | |
| CN109726195A (en) | A kind of data enhancement methods and device | |
| CN110390261A (en) | Object detection method, device, computer readable storage medium and electronic equipment | |
| CN110348109A (en) | The method and terminal device of three-dimensional artificial training data processing | |
| CN112348737A (en) | Method for generating simulation image, electronic device and storage medium | |
| CN114049536A (en) | Virtual sample generation method and device, storage medium and electronic equipment | |
| CN113642466B (en) | Living body detection and model training method, apparatus and medium | |
| CN111462043B (en) | Defect detection method, device, equipment and medium based on Internet | |
| US20150103080A1 (en) | Computing device and method for simulating point clouds | |
| CN113628170B (en) | Laser line extraction method and system based on deep learning | |
| CN112633187B (en) | Automatic robot carrying method, system and storage medium based on image analysis | |
| CN110135512A (en) | Recognition methods, equipment, storage medium and the device of picture | |
| CN112926595A (en) | Training device for deep learning neural network model, target detection system and method | |
| CN116188917B (en) | Defect data generation model training method, defect data generation method and device | |
| CN112668675A (en) | Image processing method and device, computer equipment and storage medium | |
| CN110135423A (en) | The training method and optical character recognition method of text identification network | |
| CN105719261A (en) | Point cloud data combination system and method | |
| CN115496911B (en) | Target point detection method, device, equipment and storage medium | |
| CN112308102A (en) | Image similarity calculation method, calculation device, and storage medium | |
| Gao et al. | Electronic components detection for PCBA based on a tailored YOLOv3 network with image pre-processing | |
| CN113840169A (en) | Video processing method and device, computing equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |