Fabric defect detection method based on deep convolution neural network and visual saliency

Abstract

The invention discloses a fabric defect detection method based on a deep convolution neural network and visual saliency, which belongs to the technical field of image processing. A defect region positioning module and a defect semantic segmentation module are included. The defect region positioning module uses two deep learning models of a local convolution neural network and a global convolutionneural network for fusion, advanced features of a fabric defect are extracted automatically and act on a defect image, and precise positioning of the defect region is acquired. The defect semantic segmentation module uses the defect region positioning result, a super pixel image segmentation method based on visual saliency is combined, a defect prior foreground point is acquired, a defect target is precisely segmented, and defect detection is finally realized. The multi-deep learning-fused fabric defect positioning network and the improved fabric defect segmentation network based on the visualsaliency are used, the adaptability to the fabric image is good, the precision is high, and defects in the fabric image under a complex background and noise interference can be effectively detected.

Description

technical field [0001] The invention relates to the field of visual detection in image processing, in particular to a fabric defect detection method based on deep convolutional neural network and visual saliency. Background technique [0002] With the rapid development of the textile industry, people's control on the quality of fabrics is becoming more and more strict, and fabric defects are usually the key factors affecting the quality of fabrics. Traditional fabric defect detection methods are mostly based on manual measurement and human eye observation, which have great limitations in practical applications, such as strong subjectivity, poor consistency of test results, and cannot accurately detect small defects and color differences. Complete inspection of non-obvious defects, etc. Currently, existing automated fabric defect detection algorithms are mainly classified into three categories: (1) statistical-based methods, (2) spectral analysis-based methods, and (3) model...

AI Technical Summary

Problems solved by technology

Statistics-based methods can effectively detect fabric defects by counting the different characteristics of texture and defects through local binary patterns, gray-scale co-occurrence matrices, and histogram statistics, but the impact of different fabric background patterns and defect shapes on this type of method bigger

[0003] The above research can accurately locate and segment fabric defects in a single background and a solid color background, but the defect detection effect in fabric images with complex backgrounds and irregular patterns is not good.

Images