Cloth defect detection method and system based on deep neural network

Abstract

The invention discloses a cloth defect detection method and system based on a deep neural network, and belongs to the technical field of pattern recognition. The method comprises the steps that a defect cloth image training set is used for training a deep neural network model, labels are defect types and real frame position information, the deep neural network model is composed of a backbone network and a detection network, and the backbone network is used for extracting three feature maps with different scales from defect cloth images; the detection network includesthree detection sub-networks and the detection result fusion module, wherein the three detection sub-networks are the same in structure. Each detection sub-network is used for detecting a defect type and prediction frame position information from the feature map, and consists of three dense connecting blocks, and the feature channel connection between the dense blocks is used for enhancing feature transfer, and the detection result fusion module is used for performing non-maximum suppression on the prediction result to obtain a final prediction frame and a defect type, and inputting to-be-detected cloth into the traineddeep neural network model to obtain a detection result, so that the type and the position of the defect in the cloth can be detected more quickly and accurately.

Description

technical field [0001] The invention belongs to the technical field of machine vision and pattern recognition, and more specifically, relates to a cloth defect detection method and system based on a deep neural network. Background technique [0002] my country has a large output of cloth and many manufacturers, but most of the manufacturers' products are low-end products, 80% of which produce low-end textiles, 4% of which only produce low-quality and low-price textiles, and only 4% of high-quality textile manufacturers 10% or so. In order to improve the quality of the cloth, it is necessary to detect the defects on the cloth. [0003] Due to the different shapes and complex characteristics of cloth defects, the accuracy of traditional cloth detection methods has not been high, and the traditional cloth defect detection methods are greatly affected by the external environment, have poor stability, and do not have universality. Patent CN108520114A "A textile defect detection ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the technical problems of low accuracy, poor real-time performance and lack of versatility in the existing textile defect detection method, the present invention provides a cloth defect detection method based on a deep neural network. Neural network model, faster and more accurate detection of the type and location of defects in the cloth

Images