CN112184665A - Artificial intelligence defect detecting system applied to paper-plastic industry - Google Patents
Artificial intelligence defect detecting system applied to paper-plastic industry Download PDFInfo
- Publication number
- CN112184665A CN112184665A CN202011034027.4A CN202011034027A CN112184665A CN 112184665 A CN112184665 A CN 112184665A CN 202011034027 A CN202011034027 A CN 202011034027A CN 112184665 A CN112184665 A CN 112184665A
- Authority
- CN
- China
- Prior art keywords
- defect
- artificial intelligence
- platform
- quality
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 88
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 76
- 238000001514 detection method Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000007619 statistical method Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 2
- 230000006798 recombination Effects 0.000 claims description 2
- 238000005215 recombination Methods 0.000 claims description 2
- 238000005728 strengthening Methods 0.000 claims description 2
- 238000011179 visual inspection Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 230000002950 deficient Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides an artificial intelligence defect detection system applied to the paper-plastic industry, which relates to the technical field of artificial intelligence and comprises a terminal management platform, an image capturing platform, an AI (artificial intelligence) discrimination model platform, a quality management platform and a characteristic engineering working platform; the image capturing platform performs multi-angle image capturing on a target workpiece according to preset parameters, a complete image of a target detection area of the target workpiece is obtained through splicing, and slicing processing is performed after preprocessing is performed on each angle image; the AI discrimination model platform carries out defect identification on the slices one by one through a pre-trained AI discrimination model; the quality management platform performs quality statistical analysis by combining the defect identification result; the characteristic engineering working platform performs model training on the artificial intelligence analysis model according to the multi-angle image to obtain an AI (artificial intelligence) discrimination model; and the terminal management platform visually displays the quality statistic analysis result and coordinately drives each platform. The invention can solve the problems of low efficiency and low precision of manual visual inspection.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence defect detection system applied to the paper-plastic industry.
Background
Along with the increase of labor cost and the upgrading requirement of manufacturing industry, the production line speed is continuously accelerated, the product composition is more complex, the product quality requirement of consumers is also continuously improved, particularly, the increasingly strict limitation on the environmental requirement is realized, the paper-plastic product made of recycled materials is used for gradually replacing plastic products, on one hand, the development prospect is met, on the other hand, the existing impression of the quality of the consumers is required to be met, so the detection requirement on the surface defect is relatively difficult, the quality control operation for preventing the surface defect of the paper-plastic product at present depends on manual detectors to a great extent, the upgrading and transformation of industrial automatic production make the manual detection difficult to provide absolute quality guarantee and meet the production efficiency requirement, thereby the labor cost is increased or the product detection speed is slowed down, the efficiency is low, and the misjudgment rate is increased; even if the existing relatively mature automatic visual defect detection equipment cannot meet the increasing complex and precise industrial detection requirements, manual visual rechecking is still required in the actual production process, and a lot of extra expenses are added to enterprises; the method has the advantages that limited manpower is liberated from heavy and boring repetitive work, opportunity is brought to the rapid development of the computer vision technology, more and more machine vision schemes are permeated into various fields, and defects are judged by artificial intelligence, so that the product quality and the production efficiency of the market are greatly improved.
The artificial intelligence discriminates the defect system and combines AI model verification and quality management, the AI model is set for completion before operation after deep learning, the irregular and complex image problem that the traditional vision can not process can be processed, the detection can be put into to different types of workpieces after simple setting, the operation is not different from that of an artificial visual inspector, the final result can be transmitted into a database group, and the result is presented on a quality management platform after operation, thereby facilitating the establishment of statistical analysis, rapidly finding problems, solving the problems, improving the efficiency and precision of detection, being simple in operation and saving a large amount of resources for enterprises.
The application of the AI artificial intelligence technology replaces the traditional artificial detection, can quickly acquire a large amount of information, is easy to automatically process and integrate with design information and processing control information, and improves the flexibility and the automation degree of production.
Disclosure of Invention
In view of the above disadvantages of the prior art, an object of the present invention is to provide an artificial intelligence defect detecting system applied in paper and plastic industry, so as to solve the problems of low efficiency and low precision of manual visual inspection.
The invention provides an artificial intelligence defect detection system applied to the paper-plastic industry, which comprises a terminal management platform, an image capturing platform, an AI (artificial intelligence) discrimination model platform, a quality management platform, a characteristic engineering working platform and a database group, wherein the terminal management platform is used for acquiring images of the paper-plastic industry;
the image capturing platform performs multi-angle image capturing on a target workpiece according to preset parameters, a complete image of a target detection area of the target workpiece is obtained by splicing, and slicing processing is performed after preprocessing is performed on each angle image;
the AI discrimination model platform carries out defect identification on the slices one by one through a pre-trained AI discrimination model;
the quality management platform performs quality statistical analysis by combining defect identification results, wherein the defect identification results comprise slice defect types and defect characteristic probabilities;
the database group stores the defect identification result and the quality statistical analysis result;
the characteristic engineering working platform performs model training on the artificial intelligence analysis model according to the multi-angle image to obtain an AI (artificial intelligence) discrimination model;
and the terminal management platform visually displays the quality statistic analysis result and coordinately drives each platform.
In an embodiment of the present invention, the database group includes a defect database and a quality database, the defect database stores the defect identification result, and the quality database stores the quality statistical analysis result.
In an embodiment of the invention, the defect types of the target workpiece include missing corner, abnormal color, sundries, reversed position, missing, uneven, angle offset, smudging, broken corner, color offset, color difference, and print loss.
In an embodiment of the invention, the AI discriminant model platform includes a plurality of AI discriminant models, and one AI discriminant model corresponds to all trained defect classes of a target workpiece.
In an embodiment of the invention, the preprocessing of the images at the angles includes highlighting, edge enhancement, color inversion, convolution, superimposition, and subtraction.
In one embodiment of the present invention, the defect recognition result is stored in a defect database in the form of a defect recognition probability-location matrix.
In an embodiment of the present invention, the defect identification probability-location matrix is obtained according to the size of the defect feature probability of the slice and the spatial relationship of the slice, and is recombined according to the spatial relationship of the slice, corresponding to the spatial relationship of the complete image of the target detection region of the original target workpiece.
In an embodiment of the invention, the artificial intelligence analysis model is based on a convolutional neural network, detects image features in an indeterminate region by using translation invariance of CNN, and trains according to normal samples and defect samples of known target workpieces, so that the model has defect identification capability.
As described above, the artificial intelligence defect detecting system applied to the paper-plastic industry of the present invention has the following beneficial effects: the invention can realize the automatic detection of the overall appearance of the target workpiece of the paper-plastic product, effectively improve the detection efficiency and reliability and reduce the labor cost.
Drawings
FIG. 1 is a block diagram of an artificial intelligence defect detection system according to an embodiment of the present invention.
Fig. 2 is a schematic plane structure diagram of an artificial intelligence defect detecting apparatus for paper-plastic products disclosed in the embodiment of the present invention.
Fig. 3 is a graph showing a comparison between pre-processing and post-processing of an image as disclosed in an embodiment of the present invention.
Fig. 4 is a graph showing a comparison between before and after the slicing process of the image disclosed in the embodiment of the present invention.
The labels in the figure are: 1. the system comprises a terminal management platform, 2, an image capturing platform, 3, an AI discrimination model platform, 4, a quality management platform, 5, a characteristic engineering working platform, 6, a database group, 2-1, a machine body, 2-2, a man-machine operation interface, 2-3, an industrial personal computer, 2-4, an image capturing module, 2-5, a first infrared sensor, 2-6, an algorithm machine, 2-7, a second infrared sensor, 2-8, a workpiece transmission module, 2-9 and a rejection module.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Referring to fig. 1, the present invention provides an artificial intelligence defect detecting system applied to paper and plastic industry, the system includes a terminal management platform 1, an image capturing platform 2, an AI discrimination model platform 3, a quality management platform 4, a feature engineering working platform 5, and a database group 6;
a plurality of image capturing modules of the image capturing platform 1 capture images of a target workpiece at multiple angles according to preset parameters, complete images of a target detection area of the target workpiece are obtained by splicing, and slicing processing is performed after preprocessing of each angle image, please refer to fig. 3-4; the preprocessing of the angle images comprises highlighting, edge strengthening, reverse color, convolution, superposition and subtraction processing.
The image capturing platform 1 comprises a plurality of image capturing modules capable of receiving the terminal management platform 1, and an industrial camera, a servo motor and a support which are adjusted by the image capturing modules, and the industrial camera and the target workpiece are moved to a specified position and an angle, so that the industrial camera can capture images for one time or multiple times according to a preset position, angle and time to form a multi-angle complete image of the target workpiece under a specific image capturing condition.
The system further comprises an image preprocessing program, wherein the image preprocessing program carries out pre-analysis on the target workpiece, namely, physical characteristics and image characteristics of the target workpiece are analyzed, analysis parameters are determined, the analysis parameters are transmitted to the terminal management platform 1 and the characteristic engineering working platform 5, and the terminal management platform 1 and the characteristic engineering working platform 5 set preset parameters according to the analysis parameters.
The AI discrimination model platform 3 identifies the defects of the slices one by one through a pre-trained AI discrimination model; the defect types of the target workpiece comprise unfilled corners, different colors, sundries, reversed positions, missing, unevenness, angle deviation, dirt, broken corners, color cast, color difference, print loss and the like; the AI discrimination model platform 3 comprises a plurality of AI discrimination models, and one AI discrimination model corresponds to all the trained defect categories of a target workpiece.
The quality management platform 4 performs quality statistical analysis by combining the defect identification result, that is, combines the operation data and the production data from other production equipment and production processes to jointly form a multidimensional production-defect-position data set, and performs various quality statistical analyses such as narration statistics, time series analysis, correlation analysis and the like; the defect identification result comprises a slice defect type and a defect characteristic probability.
The database group 6 stores the defect identification result and the quality statistical analysis result; the database group 6 includes a defect database that stores a defect identification result and a quality database that stores a quality statistical analysis result.
The characteristic engineering working platform 5 performs model training on the artificial intelligence analysis model according to the multi-angle image to obtain an AI (artificial intelligence) discrimination model; the artificial intelligence analysis model is based on a convolutional neural network, detects image characteristics in an uncertain region by using the translation invariance of CNN, and trains according to normal samples and defect samples of known target workpieces, so that the model has defect identification capability.
And the terminal management platform 1 visually displays the quality statistical analysis result and coordinately drives each platform.
Specifically, the defect identification result is stored in a defect database in the form of a defect identification probability-position matrix; and the defect identification probability-position matrix is obtained according to the numerical value of the defect characteristic probability of the slice and the spatial relationship recombination of the slice, and the spatial relationship of the complete image corresponding to the target detection area of the original target workpiece.
The terminal management platform 1, the image capturing platform 2, the AI discrimination model platform 3, the quality management platform 4, the characteristic engineering working platform 5 and the database group 6 can be accommodated in one device and used for workpiece defect identification application; for example, an artificial intelligence defect detecting device for paper products, a body 2-1 of the detecting device is used as a body for carrying the detecting system to detect workpieces, and an optical darkroom is formed inside the detecting device to prevent external messy light from entering.
An operator inputs relevant information of a workpiece to be detected, such as a work order number, an operator work number and the like, and inputs a name number of a detection object on a man-machine operation interface 2-2 attached to the machine body 2-1;
according to the input information, the industrial personal computer 2-3 automatically selects the corresponding AI distinguishing model, and adjusts the image capturing module 2-4 according to the corresponding parameters, and the workpiece conveying module 2-8 prepares to receive the workpiece for detection;
the workpiece conveying module 2-8 is used for conveying the workpiece to be detected, the workpiece to be detected detects that the target workpiece reaches a certain position through the first infrared sensor 2-5, the image capturing module 2-4 starts to capture images in multiple angles, and the images are transmitted to the algorithm machine 2-6 for image judgment;
after entering an algorithm machine 2-6, multi-angle image capture is firstly carried out image preprocessing, then slicing processing is carried out, wherein slicing is to divide the whole image into small pieces and small pieces of images, and finally the slices are respectively sent into an AI (artificial intelligence) discrimination model for calculation, the AI discrimination model analyzes the probability of defect characteristics in the slices according to a convolutional neural network, if the probability of defect characteristics in the AI discrimination model is more met, a higher probability of defect is given, and if the probability of defect characteristics in the AI discrimination model is less met, a lower probability of defect is given; it should be noted that the AI discrimination model after complete training is sensitive to slice images with certain adverse characteristics, and can give an obviously high adverse probability;
according to the pre-training result, the algorithm machine 2-6 can give a certain threshold value as a basis for judging good products or defective products, for example, the defective probability is higher than 0.99, and a label of the defective products is given;
acquiring a plurality of images of the same workpiece to be detected, and if the same relative position in the plurality of images is judged to be bad, directly designating the position as bad, and if a single target workpiece has a determined bad position, judging the whole target workpiece as bad;
after the target workpiece to be detected is judged to be bad, the target workpiece is continuously conveyed forwards, the target workpiece is confirmed to reach a rejection point through the second infrared sensor 2-7, the rejection module 2-9 is started, and the bad workpiece is rejected;
wherein, the workpiece to be measured marked as bad at least has one slice judged as bad; the slice is further classified, classified into various defect types, and recorded.
The embodiment of the paper-plastic product appearance defect detection equipment provided by the invention can realize automatic detection of the overall appearance of the paper-plastic product, can realize full detection of all paper-plastic products, and effectively improves the detection efficiency and reliability. In addition, the workpiece conveying modules 2-8 are matched with various mechanisms, so that shunting detection can be realized, and the detection efficiency is further improved. Meanwhile, the influence of human factors can be avoided, the detection accuracy is improved, and the labor cost is reduced. And the paper-plastic products which are unqualified in detection can be discharged through the rejecting module 2.9. Moreover, the images corresponding to the unqualified detection results stored in the image database can be used for secondary artificial inspection, and for the case of misjudgment, the detection results can be corrected to be used as new training samples of the model in the corresponding AI judgment model platform, so that the detection precision is further improved. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (8)
1. The utility model provides an artificial intelligence defect detecting system for paper industry is moulded which characterized in that: the system comprises a terminal management platform (1), an image capturing platform (2), an AI (Artificial intelligence) discrimination model platform (3), a quality management platform (4), a characteristic engineering working platform (5) and a database group (6);
the image capturing platform (1) performs multi-angle image capturing on a target workpiece according to preset parameters, splices to obtain a complete image of a target detection area of the target workpiece, and performs slicing processing after preprocessing each angle image;
the AI discrimination model platform (3) identifies the defects of the slices one by one through a pre-trained AI discrimination model;
the quality management platform (4) performs quality statistical analysis by combining defect identification results, wherein the defect identification results comprise slice defect types and defect characteristic probabilities;
the database group (6) stores the defect identification result and the quality statistical analysis result;
the characteristic engineering working platform (5) performs model training on the artificial intelligence analysis model according to the multi-angle image to obtain an AI (artificial intelligence) discrimination model;
and the terminal management platform (1) visually displays the quality statistical analysis result and coordinately drives each platform.
2. The system of claim 1, wherein the artificial intelligence defect detecting system comprises: the database group (6) comprises a defect database and a quality database, the defect database stores defect identification results, and the quality database stores quality statistic analysis results.
3. The system of claim 1, wherein the artificial intelligence defect detecting system comprises: the defect types of the target workpiece comprise unfilled corner, different colors, sundries, reversed position, missing, unevenness, angle deviation, dirt, broken corner, color deviation, color difference and print loss.
4. The system of claim 3, wherein the artificial intelligence defect detecting system comprises: the AI discrimination model platform (3) comprises a plurality of AI discrimination models, and one AI discrimination model corresponds to all trained defect categories of one target workpiece.
5. The system of claim 1, wherein the artificial intelligence defect detecting system comprises: the preprocessing of the angle images comprises highlighting, edge strengthening, reverse color, convolution, superposition and subtraction processing.
6. The system of claim 2, wherein the artificial intelligence defect detecting system comprises: the defect identification result is stored in a defect database in the form of a defect identification probability-location matrix.
7. The system of claim 6, wherein the artificial intelligence defect detecting system comprises: and the defect identification probability-position matrix is obtained according to the numerical value of the defect characteristic probability of the slice and the spatial relationship recombination of the slice, and the spatial relationship of the complete image corresponding to the target detection area of the original target workpiece.
8. The system of claim 1, wherein the artificial intelligence defect detecting system comprises: the artificial intelligence analysis model is based on a convolutional neural network, detects image characteristics in an uncertain region by using the translation invariance of CNN, and trains according to normal samples and defect samples of known target workpieces, so that the model has defect identification capability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011034027.4A CN112184665A (en) | 2020-09-27 | 2020-09-27 | Artificial intelligence defect detecting system applied to paper-plastic industry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011034027.4A CN112184665A (en) | 2020-09-27 | 2020-09-27 | Artificial intelligence defect detecting system applied to paper-plastic industry |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112184665A true CN112184665A (en) | 2021-01-05 |
Family
ID=73944668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011034027.4A Pending CN112184665A (en) | 2020-09-27 | 2020-09-27 | Artificial intelligence defect detecting system applied to paper-plastic industry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184665A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113567446A (en) * | 2021-07-06 | 2021-10-29 | 北京东方国信科技股份有限公司 | Method and system for grading component defect detection quality |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583489A (en) * | 2018-11-22 | 2019-04-05 | 中国科学院自动化研究所 | Defect classifying identification method, device, computer equipment and storage medium |
| CN109949305A (en) * | 2019-03-29 | 2019-06-28 | 北京百度网讯科技有限公司 | Method for detecting surface defects of products, device and computer equipment |
| CN110223269A (en) * | 2019-04-24 | 2019-09-10 | 深圳市派科斯科技有限公司 | A kind of FPC defect inspection method and device |
| CN110473178A (en) * | 2019-07-30 | 2019-11-19 | 上海深视信息科技有限公司 | A kind of open defect detection method and system based on multiple light courcess fusion |
| CN110726724A (en) * | 2019-10-22 | 2020-01-24 | 北京百度网讯科技有限公司 | Defect detection method, system and device |
| CN111127571A (en) * | 2019-12-03 | 2020-05-08 | 歌尔股份有限公司 | Small sample defect classification method and device |
| CN111595850A (en) * | 2020-04-27 | 2020-08-28 | 平安科技（深圳）有限公司 | Slice defect detection method, electronic device and readable storage medium |
| CN111652098A (en) * | 2020-05-25 | 2020-09-11 | 四川长虹电器股份有限公司 | Product surface defect detection method and device |
-
2020
- 2020-09-27 CN CN202011034027.4A patent/CN112184665A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583489A (en) * | 2018-11-22 | 2019-04-05 | 中国科学院自动化研究所 | Defect classifying identification method, device, computer equipment and storage medium |
| CN109949305A (en) * | 2019-03-29 | 2019-06-28 | 北京百度网讯科技有限公司 | Method for detecting surface defects of products, device and computer equipment |
| CN110223269A (en) * | 2019-04-24 | 2019-09-10 | 深圳市派科斯科技有限公司 | A kind of FPC defect inspection method and device |
| CN110473178A (en) * | 2019-07-30 | 2019-11-19 | 上海深视信息科技有限公司 | A kind of open defect detection method and system based on multiple light courcess fusion |
| CN110726724A (en) * | 2019-10-22 | 2020-01-24 | 北京百度网讯科技有限公司 | Defect detection method, system and device |
| CN111127571A (en) * | 2019-12-03 | 2020-05-08 | 歌尔股份有限公司 | Small sample defect classification method and device |
| CN111595850A (en) * | 2020-04-27 | 2020-08-28 | 平安科技（深圳）有限公司 | Slice defect detection method, electronic device and readable storage medium |
| CN111652098A (en) * | 2020-05-25 | 2020-09-11 | 四川长虹电器股份有限公司 | Product surface defect detection method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113567446A (en) * | 2021-07-06 | 2021-10-29 | 北京东方国信科技股份有限公司 | Method and system for grading component defect detection quality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179251B (en) | Defect detection system and method based on twin neural network and by utilizing template comparison | |
| CN104992449B (en) | Information identification and surface defect online test method based on machine vision | |
| CN107657603B (en) | Industrial appearance detection method based on intelligent vision | |
| CN108355981A (en) | A kind of battery connector quality determining method based on machine vision | |
| CN111667455A (en) | AI detection method for various defects of brush | |
| CN111415343B (en) | Artificial intelligence-based six-side appearance detection method for chip multilayer ceramic capacitor | |
| CN110927171A (en) | Bearing roller chamfer surface defect detection method based on machine vision | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN113083804A (en) | Laser intelligent derusting method and system and readable medium | |
| CN111179250A (en) | Industrial product defect detection system based on multitask learning | |
| CN112150439A (en) | Automatic sorting equipment and sorting method for injection molding parts | |
| CN115330734A (en) | Automatic robot repair welding system based on three-dimensional target detection and point cloud defect completion | |
| CN109693140A (en) | A kind of intelligent flexible production line and its working method | |
| CN114913346A (en) | Intelligent sorting system and method based on product color and shape recognition | |
| CN112184665A (en) | Artificial intelligence defect detecting system applied to paper-plastic industry | |
| CN112505049B (en) | Mask inhibition-based method and system for detecting surface defects of precision components | |
| CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
| CN116106319A (en) | Automatic detection method and system for defects of synthetic leather | |
| CN116977241A (en) | Method, apparatus, computer readable storage medium and computer program product for detecting defects in a vehicle component | |
| TW202326114A (en) | Fault or defect detection system for long-code zipper capable of meeting the requirement of continuous detection of the production assembly line having transmission speed at 300 m/min or lower, and has high detection precision | |
| CN116385353B (en) | Camera module abnormality detection method | |
| Undale et al. | Automatic fruit sorting system using raspberry-pi | |
| Jin et al. | Determination of defects for dynamic objects using instance segmentation | |
| Smruthi et al. | Hardware Implementation of Machine Vision System for Component Detection | |
| CN114708234A (en) | Method and device for identifying number of detonators on automatic bayonet coding all-in-one machine |
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 |