Cloth defect detection method, device and system based on machine vision

Abstract

The invention discloses a cloth defect detection method, device and system based on machine vision, and relates to the field of artificial intelligence. The method mainly comprises the following steps: obtaining membership values of pixel points according to gradient directions of the pixel points in a gray level image of a surface image of cloth to be detected; the membership values of the row / column pixel points are arranged to obtain row / column membership sequences, and row / column step length sequences corresponding to the row / column membership sequences are obtained; the permutation entropy of the row / column membership sequence is calculated, the fluctuation degree value of the row / column step length sequence is obtained according to the variance of the values contained in the row / column step length sequence, and the abnormal value of the row / column is obtained by combining the permutation entropy; arranging and fitting the abnormal value of each row / column to obtain a row / column abnormal curve; and taking a curve part between two adjacent wave troughs as a wave, obtaining the defect degree of the wave, and taking the wave with the defect degree greater than a preset first threshold value as a defect interval.

Description

technical field [0001] The present application relates to the field of artificial intelligence, and in particular to a method, device and system for fabric defect detection based on machine vision. Background technique [0002] In the textile industry, quality control plays a particularly important role, especially in the detection of fabric defects. The most common defect in the cloth is the defect, which will not only affect the appearance of the cloth, but also seriously affect the quality level of the cloth. From the raw material of the cloth to the finished cloth, it needs to go through multiple processes such as spinning, weaving, printing and dyeing. In the processing of each process, mechanical failure or negligent operation of personnel may cause defects in the appearance of the product. [0003] In the prior art, the inspection process for defects is carried out on a cloth inspection machine. The inspection personnel observe the cloth surface and find out the defe...

AI Technical Summary

Problems solved by technology

[0004] In the process of implementing the embodiment of the present invention, the inventor found that there are at least the following defects in the background technology: manual cloth inspection is a tedious and heavy labor, due to the influence of factors such as the physiology, psychology and subjective will of the inspector and the labor intensity However, it is difficult to guarantee the high accuracy and reliability of the detection results; in the cloth quality grade evaluation method based on the primitive template, the primitive template of the cloth needs to be determined in advance, and the styles of the cloth are various, so it is necessary to Constructing corresponding templates for different cloths makes the process cumbersome and not universal

Images