Cloth defect detection method using hierarchical gradient direction histogram and support vector machine

Abstract

The invention discloses a cloth defect detection method using a hierarchical gradient direction histogram and a support vector machine, relates to two aspects of feature extraction and learning classification, and belongs to the field of digital image processing application. The method mainly comprises the steps of image blocking, hierarchical gradient direction histogram feature extraction, support vector machine model training, detection classification and the like. The method comprises the following steps: firstly, partitioning a cloth image, then extracting the hierarchical gradient direction histogram characteristics of each block, then inputting the hierarchical gradient direction histogram characteristics into a trained support vector machine classifier, and judging whether each image block contains defects or not according to the output result of the classifier so as to determine whether the whole cloth image contains defects or not. Results show that the detection method has agood classification effect and certain robustness, and can be applied to actual generation.

Description

technical field [0001] The invention relates to a cloth defect detection method using a layered gradient direction histogram and a support vector machine, belonging to the application field of digital image processing. Background technique [0002] With the rapid development of China's economy, the level of production automation in the textile industry is getting higher and higher, and intelligent textile machines are continuously applied to textile enterprises, which greatly improves the production efficiency of enterprises. At the same time, the textile industry is facing increasingly fierce competition. Only by improving production technology and ensuring product quality can we obtain good returns. The presence or absence of fabric defects is an important manifestation of the quality of fabrics. Traditional defect detection is mainly done by human eyes, but there are many problems in the way of manual visual inspection, such as low recognition rate, low detection efficien...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that the false detection rate and missed detection rate of traditional artificial cloth defects are high, it is easy to cause visual fatigue of workers, the detection efficiency is low, and most of the existing cloth image detection methods are easily affected by texture features The demand for samples is large, and the purpose is to provide a cloth defect detection method using layered gradient direction histogram and SVM to solve the above problems

Images