Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method, device, equipment and medium for automatic labeling of periodic texture background defect labels

A technology of automatic labeling and texture background, applied in the field of automatic labeling of periodic texture background defect labels, which can solve the problems of low efficiency, error-prone and time-consuming human labeling data, etc.

Active Publication Date: 2020-12-01
CHENGDU UNION BIG DATA TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that human-labeled data in artificial intelligence ADC is error-prone, time-consuming and inefficient

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device, equipment and medium for automatic labeling of periodic texture background defect labels
  • Method, device, equipment and medium for automatic labeling of periodic texture background defect labels
  • Method, device, equipment and medium for automatic labeling of periodic texture background defect labels

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] The invention provides a method for automatically labeling periodic texture background defect labels, which can be applied to different computer devices, including but not limited to various personal computers, notebook computers, smart phones and tablet computers.

[0066] Such as figure 1 As shown, the present invention provides a method for automatically labeling periodic texture background defect labels, comprising the following steps:

[0067] S10: Obtain an input image, perform preprocessing on the input image, and obtain a valid image.

[0068] Among them, the input image refers to the periodic texture background image that needs to be automatically labeled with defect labels. The effective image refers to the image obtained after the input image is preprocessed.

[0069] S20: Extracting horizontal pixel information and vertical pixel information in the effective image, obtaining a horizontal cycle based on the horizontal pixel information, and obtaining a vert...

Embodiment 2

[0147] Such as Figure 7 As shown, the difference between this embodiment and Embodiment 1 is that an automatic labeling device for periodic texture background defect labels includes:

[0148] The input image processing module 10 is configured to acquire an input image, perform preprocessing on the input image, and acquire an effective image.

[0149] The effective image information extraction module 20 is configured to extract horizontal pixel information and vertical pixel information in the effective image, obtain the horizontal cycle based on the horizontal pixel information, and obtain the vertical cycle based on the vertical pixel information.

[0150] The grid partition processing module 30 is used to perform grid partition on the effective image based on the horizontal cycle and the vertical cycle, and label each grid region image after the grid partition, so that each grid region image Carries the area number.

[0151] The area difference result calculation module 4...

Embodiment 3

[0183] This embodiment provides a computer device, which may be a server, and its internal structure diagram may be as follows Figure 8shown. The computer device includes a processor, memory, network interface and database connected by a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a computer-readable storage medium and an internal memory. The computer readable storage medium stores an operating system, computer programs and databases. The internal memory provides an environment for the operation of the operating system and computer programs in the computer-readable storage medium. The database of the computer equipment is used to store the data involved in the method for automatically labeling periodic texture background defect labels or the method for network fault location and recognition. The network interface of the computer device is used to communicate w...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method, device, equipment and medium for automatically labeling periodic texture background defect labels. The method includes extracting horizontal pixel information in an effective image to obtain the horizontal cycle, and extracting vertical pixel information to obtain the vertical cycle for gridding. Partition the effective image, label each grid area image after grid partitioning; process the pixels in the grid area image differentially through the adjacent difference analysis method, obtain the regional difference result, and then obtain the differential feature information; based on the differential feature information Construct the abnormal area, and perform absolute value difference processing between the abnormal area and the target normal area, and then use the kernel window to perform the opening operation on the result of the absolute value difference processing, and finally perform regularization and binarization processing on the opening operation result to obtain the defect image , so as to obtain the defect contour and mark the defect position on the defect contour, without manual marking, and improve the marking accuracy and marking efficiency.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method, device, equipment and medium for automatic labeling of periodic texture background defect labels. Background technique [0002] In the process of industrial manufacturing, especially electronic manufacturing products, products will inevitably produce various defects. At present, AOI (Automated Optical Inspection) equipment is mainly used to detect and identify defects in products through template matching, and then Classify the defect photos taken by AOI equipment through a lot of manpower. In the era of Industry 2.0, more and more electronics manufacturers have begun to use artificial intelligence ADC (Automatic Defect Classification System) to replace manpower for defect classification. However, artificial intelligence ADC requires a large amount of labeled data for model training, and currently labeled data are all It requires a lot of manpower to mark, whi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06K9/46
CPCG06T7/0004G06V10/44
Inventor 不公告发明人
Owner CHENGDU UNION BIG DATA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com