织物疵点自动检测方法及应用进展  

Methods and A pplication of Automatic Fabric Defects Detection

作　　者：张露 朱文俊 祝双武 ZHANG Lu;ZHU Wen-jun;ZHU Shuang-wu(Xi'an Polytechnic University,Xi'an 710048,China)

机构地区：[1]西安工程大学纺织科学与工程学院,陕西西安710048

出　　处：《纺织科技进展》2022年第2期21-26,共6页Progress in Textile Science & Technology

摘　　要：织物疵点是影响织物价格的重要因素,一直以来都备受关注。随着科学技术的发展,对智能化需求的提高,织物疵点的自动检测成为纺织行业的热门话题。织物疵点自动检测系统在市场上已经有了较为成熟的产品,国内的主流方式仍为机下检测,对平整布面检测效果较好。根据图像处理的方法可将检测算法分为结构法、统计法、频谱分析法、基于模型的方法、基于学习的方法五类,分析结果显示,方法的交叉混合在实际应用中往往效果更好、更受青睐。未来织物疵点自动检测方法将继续向实时性、普适性方向发展,实现多方向多尺度疵点在不同织物背景下的可预测性。As an important factor affecting fabric prices,fabric defects had attracted much attention.With the development of science and technology and the improvement of the demand for intelligence,automatic detection of fabric defects had become a hot topic in the textile industry.There were some mature products about the automatic detection system of fabric defects in the market.But the main detection method in China was still after weaving,and had a good detection effect on the fabric with flat surface.According to the methods of image processing,detection algorithms could be divided into five categories:structure method,statistical method,spectrum method,model-based method and learning based method.The cross mixing of methods was more popular in practical application.In the future,automatic fabric defect detection methods will continue to develop towards real-time and universal direction,and the predictability of multi-direction and multi-scale defects in different fabric backgrounds will be achieved.

关 键 词：织物疵点检测 图像处理 图像识别 检测算法 

分 类 号：TS101.9[轻工技术与工程—纺织工程]