Dual-simplified pulse coupled neural network-based grey cloth defect division method

A technology of pulse-coupled nerves and defects, applied in image data processing, instruments, calculations, etc., can solve the problems of multiple adjustment parameters and high computational complexity

Inactive Publication Date: 2012-07-18
XI'AN POLYTECHNIC UNIVERSITY
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a gray cloth defect segmentation method based on double-simplified pulse-coupled neural network, which solves the problems of many adjustment parameters and high computational complexity existing in the existing gray cloth defect segmentation technology, and improves the consistency and accuracy of gray cloth defect detection. Accuracy to meet the real-time and adaptive processing requirements of online defect detection

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
  • Dual-simplified pulse coupled neural network-based grey cloth defect division method
  • Dual-simplified pulse coupled neural network-based grey cloth defect division method
  • Dual-simplified pulse coupled neural network-based grey cloth defect division method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0050] The principle of the method of the present invention is that firstly, the original digital image of the gray cloth to be tested with the size of M×N collected by the camera is divided into non-overlapping windows of the size of n×n; The local binary modulus sum corresponding to the variability of the average attribute value of the row and column pixels, and then calculate the binary modulus difference between the row and column as the feature value in the window, and obtain a The characteristic image of the gray cloth to be tested in the size. Then, divide the feature image of K×L size into overlapping windows of m×m size, each pixel in the image corresponds to each neuron in DSPCNN, and the attribute intensity value of the pixel g ij As the neuron external stimulus input N ij , according to the characteristics of human vision, unde...

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 dual-simplified pulse coupled neural network-based grey cloth defect division method, which comprises the following steps of: firstly, acquiring a digital image of grey cloth with the size of M*N by using a camera, and transmitting the digital image to an image cache; secondly, performing defect characteristic extraction calculation on the digital image in the image cache by adopting a local binary pattern arithmetic operator to eliminate the influence of illumination non-uniformity, a texture background and noise interference and highlight a defect area, and simultaneously compressing the calculated image into one-(n*n)th of the original image; thirdly, performing iteration calculation for high and low luminance grey cloth defect division on a processing result image by adopting a dual source pulse coupled neural network (DSPCNN); and finally, judging whether iteration is performed to set iteration times t or not, and performing merging calculation on a DSPCNN processing result to obtain a grey cloth defect division result diagram S. By the method, the problems of many regulation parameters, high calculation complexity and non-adaptability of the conventional grey cloth defect division technology are solved, and the real-time performance, consistence and accuracy of grey cloth defect detection are improved.

Description

technical field [0001] The invention belongs to the technical field of digital image segmentation, and relates to a gray cloth defect segmentation method, in particular to a gray cloth defect segmentation method based on a double-simplified pulse coupling neural network. Background technique [0002] With the increasingly fierce competition in the international textile market, the quality of textiles has increasingly become a winning factor for the survival and development of enterprises. Defect detection is an important part of textile quality control. For a long time, domestic gray fabric factories have mostly relied on manual detection of defects. Due to long-term eye fatigue or subjective factors of inspectors, problems such as missed inspections or inconsistent inspection results have also directly affected the quality of subsequent products. objective assessment. Therefore, improving the accuracy of gray cloth defect detection has become an indispensable core technol...

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
IPC IPC(8): G06T5/00
Inventor 石美红姜寿山郭勇刚宁长胜马进朝
Owner XI'AN POLYTECHNIC UNIVERSITY
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