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

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...

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

Images