A Textile Surface Defect Detection Method Based on Image Processing Technology

Abstract

The present invention relates to a method for detecting defects on the surface of textiles based on image processing technology. The method includes the following steps: Step 1: Use artificial neural network to determine and classify the type and color of silk threads used in fabrics, and use artificial neural network technology Extract and select the color scheme data; Step 2: Weave according to the predetermined weaving scheme; Step 3: Collect the fabric image, and use the Gabor filter to detect the fabric image, and mark and segment the defect points in the fabric image. The present invention detects the defect points on the fabric image by using the odd-symmetrical Gabor filter and the even-symmetrical Gabor filter, thereby increasing the accuracy of defect point detection, which is beneficial to analyze the causes of fabric defects and modify them, thereby increasing the number of fabric defects. production efficiency.

Description

technical field [0001] The invention relates to the technical field of textile technology, in particular to a method for detecting defects on the surface of textiles based on image processing technology. Background technique [0002] With the development of the times and the advancement of science and technology, the fabrics brought by the existing brocade technology take a lot of time in production because of the complex process, so that the production quantity of the fabrics cannot meet the market demand. One of the reasons is that the fabrics In the process of weaving, there are often a lot of defects in the finished fabric due to machine or human errors, and in the process of fabric design, due to the difference in the coloring degree of the fabric, there are many differences between the fabric design and the fabric entity. . [0003] In the textile industry, cloth defect inspection is an important link, but most domestic and foreign enterprises still use traditional ma...

AI Technical Summary

Problems solved by technology

[0005] Algorithms based on statistical features include: grayscale statistical method, fractal dimension defect point detection method, morphological algorithm and defect point detection algorithm based on co-occurrence gray moment features. These four algorithms have many problems in practical applications. large limitations, while detection algorithms based on spectral analysis are expensive and not suitable for random texture materials

[0006] Due to the characteristics of non-parametric influence, the fabric defect detection algorithm based on neural network has been proved to have a good performance in the detection of complex fabric defect points, and the training and calculation process of the network is relatively simple, but in the actual application process, Detection errors are often caused by wrinkles, light, etc., resulting in low detection accuracy

Images