基于十字窗口的经编织物疵点检测  

Fabric defect detection based on the cross window method

作　　者：杜帅 李岳阳 夏风林 罗海驰 蒋高明[1] DU Shuai;LI Yueyang;XIA Fenglin;LUO Haichi;JIANG Gaoming(Engineering Research Center for Knitting Technology,Ministry of Education,Ministry of Education,Jiangnan University,Wuxi 214122,China;Key Laboratory of Advanced Process Control for Light Industry,Ministry of Education,Jiangnan University,Wuxi 214122,China)

机构地区：[1]江南大学教育部针织技术工程研究中心,江苏无锡214122 [2]江南大学轻工过程先进控制教育部重点实验室,江苏无锡214122

出　　处：《丝绸》2019年第11期26-31,共6页Journal of Silk

基　　金：中央高校基本科研业务费专项资金-重点项目(JUSRP51727A);湖北省纺织新材料及其应用国家重点实验室项目(DTL2017009)

摘　　要：织物疵点检测在织物的质量控制中起着重要作用,传统的疵点检测方法,实际应用中会出现检测灵敏度差、虚警率高等问题,为此文章采用了一种十字窗口的方法来进行织物疵点检测。首先利用同态滤波对图像进行预处理,然后以滤波后的像素点为中心点,其上下左右四个方向上选择邻近像素点,根据中心点与邻近像素点的灰度差值,从而判断中心点的类别。实验结果表明:该算法对疵点背景分离明显的疵点具有很好的检测效果,不仅能检测出光照不匀情况下的弱小疵点,也能检测不同类型的弱小疵点,检测正确率可达94.44%,具有一定的适应性、检出率及抗噪性。Fabric defect detection plays an important role in fabric quality control. Traditional defect detection methods have such problems as poor sensitivity and high false alarm rate in the actual detection. Therefore, a cross window method was adopted to detect fabric defects. Firstly, the image was preprocessed by homomorphic filtering. Then, the pixel point after smoothing was taken as the central point, and adjacent pixel points were chosen around the central point. The category of central point was thus judged according to gray level difference between the central point and adjacent pixel points. The experiment results show that the method has the better effect on the defects with obvious separation of defect and background. It can not only detect the small defects under the condition of uneven illumination, but also effectively detect different types of small defects. The detection rate can reach 94.44%. The method has certain adaptability, detection rate and anti-interference.

关 键 词：疵点检测 十字窗口 同态滤波 阈值分割 局部差分法 

分 类 号：TS106.56[轻工技术与工程—纺织工程] TS101.97[轻工技术与工程—纺织科学与工程]