Image defect recognition method and system, electronic equipment and storage medium

A defect recognition and image technology, applied in the field of image processing, can solve problems such as low detection efficiency and neglect of similarity, and achieve good recognition, broad market prospects and application value

Inactive Publication Date: 2018-04-06
苏州珂锐铁电气科技有限公司
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing image defect detection methods have the following problems: the similarity of the same type of defects in the surface image is ignored, resulting in low detection efficiency

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
  • Image defect recognition method and system, electronic equipment and storage medium
  • Image defect recognition method and system, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Below, in conjunction with accompanying drawing and specific embodiment, the present invention is described further:

[0033] Such as figure 1 As shown, it is a schematic diagram of an image recognition method in an embodiment of the present invention, and the method includes the following steps:

[0034] Step 110, using each row of pixels and each column of pixels in the image as a chaotic time series, and calculating the chaotic features of each chaotic time series;

[0035] Step 120, establishing chaotic eigenvectors for the chaotic features of each chaotic time series to obtain a chaotic eigenvector matrix;

[0036] Step 130, using a clustering algorithm to cluster the eigenvector matrix of the training samples to obtain a codebook;

[0037] Step 140, calculate the histogram of each training image with the bag of words model according to the code book, and then calculate the histogram of the test image;

[0038] Step 150, building a model for the histogram featur...

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 an image defect recognition method and system, electronic equipment and a storage medium. The method comprises the following steps of: respectively taking each row of pixels and each column of pixels in an image as chaotic time sequences and calculating a chaotic feature of each chaotic time sequence; respectively a chaotic feature vector for the chaotic feature of each chaotic time sequence; clustering a chaotic feature vector matrix of a training sample by utilizing a clustering algorithm so as to obtain a code book; calculating histograms of each training image and each test image according to a bag of words mode for code books; establishing group sparse models for the histograms of the training images and the test images through a multi-task learning method; calculating the group sparse models by utilizing an alternating direction multiplier algorithm; and classifying defect images by utilizing reconstruction errors. According to the method, surface defectscan be better recognized and the correctness is high; and the method can be applied to various civil and military systems such as face recognition and military target tracking recognition systems, andhas wide market prospect and application value.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image defect recognition method, electronic equipment, storage media and a system. Background technique [0002] Defect detection plays an important role in industrial automation. Traditional detection methods mostly use physical measurement to detect defects. Image defect detection uses images to achieve detection purposes. Compared with traditional methods, defects can be seen more intuitively. The existing image defect detection methods have the following problems: the similarity of the same type of defects in the surface image is ignored, resulting in low detection efficiency. Contents of the invention [0003] In view of the deficiencies in the prior art, one of the purposes of the present invention is to provide a method for identifying image defects, the method comprising the following steps: [0004] Each row of pixels and each column of pixels in the image...

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 Applications(China)
IPC IPC(8): G06T7/00G06K9/62G01N21/88
CPCG06T7/0004G01N21/8851G01N2021/8887G06T2207/20081G06T2207/10004G06F18/23G06F18/24
Inventor 罗新斌王勇
Owner 苏州珂锐铁电气科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap