CN112422952A - Intelligent detection integrated workstation - Google Patents
Intelligent detection integrated workstation Download PDFInfo
- Publication number
- CN112422952A CN112422952A CN202011141642.5A CN202011141642A CN112422952A CN 112422952 A CN112422952 A CN 112422952A CN 202011141642 A CN202011141642 A CN 202011141642A CN 112422952 A CN112422952 A CN 112422952A
- Authority
- CN
- China
- Prior art keywords
- image
- function
- detection
- quality
- display
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 72
- 230000007547 defect Effects 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000003326 Quality management system Methods 0.000 claims abstract description 19
- 238000003860 storage Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 76
- 238000000034 method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 19
- 238000005192 partition Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 238000004049 embossing Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000013441 quality evaluation Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000009795 derivation Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 5
- 230000004438 eyesight Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000001303 quality assessment method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
-
- 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
- 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
Abstract
The invention discloses an intelligent detection integrated workstation, which comprises an image acquisition system, an image detection system, a quality management system, an equipment management system and a display system, wherein the image acquisition system is connected with the quality management system; an image acquisition device in the image acquisition system acquires a target image from the outside, converts the format and stores the image by an image storage function; the image is adjusted and processed by basic processing and advanced processing in the image detection system, the image is displayed on a display by an image display function, a standard image of a current target object is selected in an image comparison function to be compared and labeled with an acquired image, a detection mode is selected in an intelligent defect detection function, and the intelligent defect detection system performs related data preprocessing on the image, and performs defect screening, positioning and grading. And after the detection is finished, submitting and approving the image, and sending the image to a quality management system after the image is reevaluated by a related technical expert, wherein the quality management system generates a quality report according to a target template and the processing information of the current image to finish the detection.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to an intelligent detection integrated workstation.
Background
More and more modern industrial manufacturers are using computer vision technology to check industrial products for problems and improve quality.
And (4) taking a new generation of artificial intelligence and machine vision technology as the leading industrial quality inspection equipment to step on the stage. How AI helps the industrial quality inspection intellectualization, as the artificial intelligence field leads the enterprise, fully grasps the customer core requirements in the industrial detection field, starts with the industry pain point and develops a series of technologies and products for solving the industry pain point, and enables the industrial field with the advanced AI industrial vision technology.
Relevant statistics show that china performs visual inspections on production lines daily for over 350 million workers, with over 150 million people in the 3C industry alone. The quality testing personnel spend a great deal of time to judge the quality of the industrial parts every day, which not only harms the eyesight of the personnel, but also has the problems of poor speed and stability and the like, and influences the testing efficiency and the quality; meanwhile, the traditional industrial quality inspection method designs a judgment rule by manually selecting the characteristics of brightness, color, size, shape and the like and parameters thereof by using various tools such as a magnifying glass, a microscope and the like through experiments, can only judge quantitative defect detection and cannot be self-adaptive, and has low universality and high labor cost. In addition, after GDP surpasses Japan, the conversion of new and old kinetic energy becomes a trend; however, in the conversion process, weapons which can be selected by customers are too old and outdated, the traditional machine vision technology has been developed for decades, and under the condition that the requirement exists in the manufacturing industry, 80% or even 90% of vision intelligentization blanks certainly exist, which shows that the traditional scheme has too high limitation, too high cost and too complex implementation scheme.
Disclosure of Invention
Aiming at the technical problems of low labor efficiency and poor stability, the invention provides an intelligent detection integrated workstation.
In order to achieve the purpose, the invention is realized by the following technical scheme:
an intelligent detection integrated workstation comprises an image acquisition system, an image detection system, a quality management system, an equipment management system and a display system; the image acquisition system is responsible for acquiring images from the outside, the acquired images are transmitted to the image detection system, the image detection system performs defect detection on the images and labels the defective images, and after the labeling is completed, the quality management system performs quality evaluation on the images and then automatically generates a quality report; the equipment management system monitors the working state of a connecting port of the image acquisition system; the display system displays the quality evaluation report of the quality management system on the display.
Compared with the prior art, the invention has the following advantages: the system can be accessed to various information acquisition devices, covers a defect detection algorithm of multi-field and multi-type components based on deep learning, automatically and intelligently generates a quality detection report, monitors the working state of the equipment in real time and tracks the health state of the equipment. The defect detection method aims to solve the problems of low detection efficiency and low accuracy rate in the prior art by utilizing a manual or traditional defect detection method.
More preferably: the image acquisition system is responsible for acquiring images from external acquisition equipment to the system or uploading image data and reading network shared image data; the system mainly comprises an equipment access function, an image acquisition function, an image conversion function and an image storage function;
the equipment access function is connected with the acquisition equipment through an interface;
the image acquisition function is used for uploading image data acquired by acquisition equipment or reading network sharing image data;
the image conversion function converts images with different formats into the image format of the cost system;
the image storage function stores the image acquisition data;
the target image is an image acquired by the acquisition function.
By adopting the technical scheme, the acquisition equipment in the image acquisition system can be connected with the detection equipment, the scanner, the camera and the acquisition camera device to sample and collect the image. The image data acquisition function can be realized in a network downloading and sharing mode, the format of the image data is adjusted after the acquisition is finished, and the image data is stored after the image data is uniformly adjusted to the image format supported by the workstation.
More preferably: the intelligent image detection system mainly comprises an image display function, a basic processing function, an advanced processing function, an image labeling function, an image comparison function and an intelligent defect detection function;
the image display function displays the acquired image data into an image;
the basic processing function comprises basic information display of the image, adjustment of the window width and the window level of the image, movement, scaling, rotation, overturning, brightness adjustment, contrast adjustment and white reflection processing;
advanced processing functions include various modifications of the image: sharpening, embossing, smoothing, edge detection, image enhancement, binarization, histogram equalization, power transformation, Hough transformation and morphology;
the image marking comprises marking basic information such as resolution, signal-to-noise ratio, workpiece name, time and the like, and also supports linear, arrow, angle, rectangle, circle, character marking and free drawing of graphic information on the image;
the image contrast function supports two contrast modes of 2 frames and 4 frames. Selecting a standard image of the current workpiece from a standard image library, and comparing the standard image with the currently acquired image;
the intelligent defect detection function comprises intelligent defect screening, positioning, classifying, grading and reevaluation, and meanwhile, manual quality assessment is supported.
By adopting the technical scheme, the image can be displayed on the display system by the basic processing function, the standard image is picked from the image library for comparison after the image is processed by the basic processing function and the advanced processing function, and the defects of the image are evaluated.
More preferably: the quality management system mainly comprises the functions of quality report generation, quality report editing, quality report export, quality report printing and the like;
the report generation is to generate a quality report for the workpiece according to the self-defined report template and the defect detection function;
quality report editing means that the quality report can be manually created, entered and edited.
Quality report derivation means that the quality report can be electronically derived including: word, PDF, picture format.
Quality report printing refers to the ability to print quality reports on paper.
By adopting the technical scheme, the quality management system prints and edits the quality report to provide more personalized choices for users, thereby being convenient for different requirements in actual use.
The method is further optimized as follows: the equipment management system is mainly used for monitoring and early warning the running state and the health state of the image acquisition related equipment.
By adopting the technical scheme, the equipment management system monitors the running condition of the equipment and pre-warns to ensure the smooth running of the workstation.
The method is further optimized as follows: the display system is mainly responsible for visually displaying an image acquisition process, an image processing process, an intelligent detection process, a quality report generation process and the like, is divided into five partitions including a console, an image acquisition partition, an image preprocessing partition, an image detection partition and a quality report partition by default, and can freely set the visual partitions through parameters. .
By adopting the technical scheme, the display system respectively displays the console, the image acquisition, the image preprocessing, the image detection and the quality report on the display.
Drawings
Fig. 1 is a schematic structural composition diagram of an intelligent detection integrated workstation according to this embodiment;
fig. 2 is a schematic diagram of a workflow of an intelligent detection integrated workstation according to this embodiment.
Detailed Description
The present invention will be described in further detail with reference to fig. 1 and 2.
An intelligent detection integrated workstation is used for image intelligent detection and comprises an image acquisition system, an image detection system, a quality management system, an equipment management system and a display system, wherein the image acquisition system, the image detection system, the quality management system, the equipment management system and the display system are arranged in the image acquisition system; the image acquisition system is responsible for acquiring images from the outside, the acquired images are transmitted to the image detection system, the image detection system performs defect detection on the images and labels the defective images, and after the labeling is completed, the quality management system performs quality evaluation on the images and then automatically generates a quality report; the equipment management system monitors the working state of a connecting port of the image acquisition system; the presentation system displays the quality assessment report of the quality management system on the display.
The workstation consists of five functional modules, and comprises an image acquisition system, an image detection system, a quality management system, an equipment management system and a display system.
The image acquisition system is responsible for acquiring digital ray images of workpieces from external acquisition equipment to the system or uploading image data and reading network shared image data. The system mainly comprises equipment access functions, image acquisition functions, image conversion functions and image storage functions, wherein the equipment access functions are to integrate a workpiece digital ray instrument through an interface and directly control imaging related operations, and the image acquisition functions are responsible for acquiring image data from acquisition equipment or uploading the image data and reading network shared image data; the image conversion is responsible for converting images with different formats into image formats which are unified by the system. The intelligent recognition defect model supports sub-updates. And the self-updating mechanism updates the deep neural network based on the content for feedback in a certain time interval. Update time, once a week (22-23 points per wednesday), if the amount of data fed back exceeds 500 (adjustable) pieces.
The image detection system mainly comprises an image display function, a basic processing function, an advanced processing function, an image labeling function, an image comparison function, an image storage function, a defect screening function, a defect positioning function, a defect classification function and a defect grading function, wherein a detection mode is selected from the intelligent defect detection function, and the intelligent defect detection system performs related data preprocessing on the image, and performs defect screening, positioning and grading. After the detection is finished, submitting and approving the images, and sending the images to a quality management system after the images are reevaluated by the experts in the related art. The image display displays the acquired image data into an image and supports multi-format images such as 8-bit images, 16-bit images and the like. And processing the newly acquired image by default and supporting the processing of the image acquired historically. The basic processing comprises basic information display of the image, adjustment of window width and window level, movement, scaling, rotation, overturning, brightness adjustment, contrast adjustment and white reflection processing. Advanced processing includes various advanced filters of the image: sharpening, embossing, smoothing, edge detection, image enhancement, binarization, histogram equalization, power transformation, Hough transformation and morphology. The image marking comprises basic information marking such as resolution, signal-to-noise ratio, workpiece name, time and the like, and also supports straight line, arrow, angle, rectangle, circle, character marking and free drawing of graphs on the image. The image contrast supports two modes of 2 frames and 4 frames. And selecting a standard image of the current workpiece from a standard image library, and comparing the standard image with the currently acquired image. And the image storage stores the processed and marked images. The intelligent defect detection comprises intelligent defect screening, positioning, classification, grading and reevaluation, and meanwhile, manual quality assessment is supported.
The quality management system is mainly divided into functions of automatically generating reports, editing reports, printing reports, exporting reports and the like. The automatic generation of the report is to automatically generate a workpiece quality report according to the self-defined report template and the acquisition and processing information of the current workpiece ray image. The quality report can be manually created, entered, and edited. The quality report supports printing. The quality report supports three format derivation: word, PDF, image format.
The equipment management system mainly collects the monitoring and early warning of the running state and the health state of the relevant equipment according to images.
The display system is mainly responsible for visually displaying an image acquisition process, an image processing process, an intelligent detection process, a quality report generation process and the like, is divided into five partitions including a console, an image acquisition partition, an image preprocessing partition, an image detection partition and a quality report partition by default, and can freely set the visual partitions through parameters.
Referring to FIG. 2, the workstation operation includes the following steps
Firstly, accessing acquisition equipment to be responsible for accessing information acquisition equipment.
And step two, image acquisition is carried out, and the digital ray image of the workpiece is acquired from an external acquisition device to the system or the image data is uploaded and the network sharing image data is read. The image conversion function is used to convert different image formats into special standard formats. And the collected images are stored in a database by utilizing an image storage function, so that users can search and export the images.
And step three, selecting a process, namely selecting a process file of the current workpiece to be detected.
And step four, processing the collected images according to the selected process files, displaying the collected images by using an image display function, and enabling a user to select and display 8-bit or 16-bit images. And processing the image by using a basic processing function, wherein the basic processing function comprises adjustment, movement, scaling and the like of the window width and the window level of the image. The advanced filtering of the image, including sharpening, embossing, smoothing, etc., is accomplished using advanced processing functions. And marking the image fineness including the resolution, the signal-to-noise ratio, the workpiece name, the time and other basic information by using an image marking function. And performing defect detection on the processed images, and finishing the defect detection classification of the existing images by a user based on a trained deep learning algorithm model, or dividing a training set and a test set from a database according to the self requirement, training a specific defect detection model based on the deep learning algorithm, finishing the classification of the defect images, obtaining the defective images and finishing the specific requirement. And carrying out defect identification, classification and rating on the determined defective images by using the trained defect marking deep learning model, and marking the positions of the defects. The user can upload the trained model to the cloud end for sharing according to the self requirement, and the model is convenient for a third party to call.
And step five, after the image detection is finished, the quality of the part is evaluated, the quality of the part without the defect is confirmed, the part with the defect is specially marked, and the position of the defect is marked.
And step six, automatically generating a quality report. The user can edit the report after the report is finished, add contents such as defect types, severity and the like, and then finish the report printing and the report exporting according to the operation.
The present embodiment is only for explaining the invention, and it is not limited to the invention, and those skilled in the art can make modifications to the embodiment as necessary without inventive contribution after reading the present specification, but all of them are protected by the patent law within the scope of the present invention.
Claims (6)
1. The utility model provides an intellectual detection system integration workstation, includes the workstation, its characterized in that:
the workstation comprises an image acquisition system, an image detection system, a quality management system, an equipment management system and a display system; the image acquisition system converts the format of a target image after acquiring the target image and stores the image, and then transmits the target image to the image detection system, the image detection system detects the defect of the target image and marks the defective target image, the quality management system evaluates the quality of the target image and generates a quality report; the equipment management system is used for monitoring the working state of a connecting port of the image acquisition system; the display system displays the quality evaluation report of the target image on a display.
2. The intelligent detection integrated workstation of claim 1, wherein: the image acquisition system includes: the device comprises a device access function, an image acquisition function, an image conversion function and an image storage function;
the equipment access function is realized by connecting an interface with acquisition equipment;
the image acquisition function includes: collecting data of the target image from a collecting device; uploading local image data; reading network sharing image data;
the image conversion function converts the acquired images with different formats into a uniform image format;
and the image storage function stores the acquired image data.
3. The intelligent detection integrated workstation of claim 1, wherein: the image detection system includes: the system comprises an image display function, a basic processing function, an advanced processing function, an image marking function, an image comparison function, a defect screening function, a defect positioning function, a defect classification function and a defect grading function;
the image display function converts the acquired image data into an image which can be displayed on a display;
the basic processing functions include: basic information display of the image, adjustment of the window width and the window level of the image, movement, scaling, rotation, overturning, brightness adjustment, contrast adjustment and white reflection processing;
the high-level processing functions including modification of the image include: sharpening, embossing, smoothing, edge detection, image enhancement, binarization, histogram equalization, power transformation, Hough transformation and morphology;
the image labeling function comprises: the method comprises the following steps of (1) marking resolution, signal-to-noise ratio, workpiece name, time and basic information, wherein the image marking supports the information of straight lines, arrows, angles, rectangles, circles, free drawing graphs and character marks on an image;
the image comparison function supports two comparison modes of 2 frames and 4 frames, and selects a standard image of a current workpiece from a standard image library and compares the standard image with a currently acquired image;
the defect detection function includes: intelligent defect detection, artificial defect detection and man-machine cooperation defect detection.
4. The intelligent detection integrated workstation of claim 1, wherein: the quality management system mainly comprises the functions of quality report generation, quality report editing, quality report export, quality report printing and the like;
the quality report generation is to generate a quality report after grading the workpiece according to a self-defined report template and the defect detection function;
the quality report editing means that the quality report can be manually created, recorded and edited;
the quality report derivation means that the quality report can be derived in an electronic format, including: word, PDF, picture format.
The quality report printing means that the quality report can be printed on paper.
5. The intelligent detection integrated workstation of claim 1, wherein: the equipment management system is mainly used for monitoring and early warning the running state and the health state of relevant equipment of the workstation.
6. The intelligent detection integrated workstation of claim 1, wherein: the display system is mainly responsible for displaying a visual display image acquisition process, an image processing process, an intelligent detection process, a quality report generation process and the like, and is divided into five partitions including a console, an image acquisition process, an image preprocessing process, an image detection process and a quality report by default to be displayed on a display of the workstation, and the visual partitions can be freely set through parameters in partition display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141642.5A CN112422952A (en) | 2020-10-22 | 2020-10-22 | Intelligent detection integrated workstation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141642.5A CN112422952A (en) | 2020-10-22 | 2020-10-22 | Intelligent detection integrated workstation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112422952A true CN112422952A (en) | 2021-02-26 |
Family
ID=74840927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011141642.5A Pending CN112422952A (en) | 2020-10-22 | 2020-10-22 | Intelligent detection integrated workstation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112422952A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202002894U (en) * | 2011-01-10 | 2011-10-05 | 山东轻工业学院 | Quick online paper flaw detecting system based on machine vision |
| US20130251219A1 (en) * | 2012-03-20 | 2013-09-26 | Siemens Medical Solutions Usa, Inc. | Medical Image Quality Monitoring and Improvement System |
| CN111429454A (en) * | 2020-04-21 | 2020-07-17 | 西安数合信息科技有限公司 | Intelligent casting nondestructive testing system and method |
| CN111539923A (en) * | 2020-04-17 | 2020-08-14 | 西安数合信息科技有限公司 | Digital ray detection method and system for weld defects and server |
-
2020
- 2020-10-22 CN CN202011141642.5A patent/CN112422952A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202002894U (en) * | 2011-01-10 | 2011-10-05 | 山东轻工业学院 | Quick online paper flaw detecting system based on machine vision |
| US20130251219A1 (en) * | 2012-03-20 | 2013-09-26 | Siemens Medical Solutions Usa, Inc. | Medical Image Quality Monitoring and Improvement System |
| CN111539923A (en) * | 2020-04-17 | 2020-08-14 | 西安数合信息科技有限公司 | Digital ray detection method and system for weld defects and server |
| CN111429454A (en) * | 2020-04-21 | 2020-07-17 | 西安数合信息科技有限公司 | Intelligent casting nondestructive testing system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108355987B (en) | A kind of screen printing of battery quality determining method based on piecemeal template matching | |
| CN106556611A (en) | Chromatograp defect automatic checkout system and detection method based on machine vision | |
| CN111539923A (en) | Digital ray detection method and system for weld defects and server | |
| CN109856156A (en) | A kind of display panel tiny flaw determination method and device based on AOI | |
| CN104102912A (en) | Sub-item metering energy consumption data collection device based on video image identification and method thereof | |
| CN113083804A (en) | Laser intelligent derusting method and system and readable medium | |
| CN112258460A (en) | Printed product quality real-time monitoring and quality inspection system based on image recognition | |
| CN108627520A (en) | A kind of on-line detecting system and method for heterogeneous solid material presentation quality | |
| CN114255334B (en) | Shape feature acquisition device, database and identification system for traditional Chinese medicine | |
| CN107024478A (en) | A kind of part processes automatic defect identifying system | |
| CN102601131A (en) | Steel billet surface quality online detection device | |
| CN113325001A (en) | Automatic distinguishing and detecting equipment and method for surface appearance flaws of copper foil | |
| CN111429454A (en) | Intelligent casting nondestructive testing system and method | |
| CN112730326A (en) | Intelligent identification device and method for rock slices | |
| CN113588656A (en) | Novel bolt appearance size detection method | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN110533660B (en) | Method for detecting silk-screen defect of electronic product shell | |
| CN113588653A (en) | System and method for detecting and tracking quality of aluminum anode carbon block | |
| CN112422952A (en) | Intelligent detection integrated workstation | |
| CN102735689A (en) | Paper defect detection system based on image pattern recognition | |
| CN109145912A (en) | A kind of digital instrument reading automatic identifying method | |
| CN112991324A (en) | Detection method for visual transmission in magnetic particle detection process | |
| CN114494142A (en) | Mobile terminal middle frame defect detection method and device based on deep learning | |
| CN112598503A (en) | OCR recognition system and method based on credit investigation recognition | |
| CN111028289A (en) | Method for positioning foreign matters in equipment in transformer substation based on template matching |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |
|
| RJ01 | Rejection of invention patent application after publication |