基于小波模极大值和自适应Canny算子的织物疵点检测算法  

Fabric Defect Detection Algorithm Based on Wavelet Modulus Maxima and Adaptive Canny Operator

作　　者：陈玉婷 刘洞波[1] 施怡澄 高樱萍 CHEN Yuting;LIU Dongbo;SHI Yicheng;GAO Yingping(College of Computer Science and Communications,Hunan Institute of Engineering,Xiangtan 411104,China)

机构地区：[1]湖南工程学院计算机与通信学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2022年第2期54-58,65,共6页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省自然科学基金资助项目(2020JJ6022).

摘　　要：为解决传统人工检测织物疵点时准确率和效率低、经典Canny算子无法自适应平滑和自适应阈值选择的问题,提出一种小波模极大值算法和自适应Canny算子结合的织物疵点检测算法.将自适应Canny算子和小波模极大值算法提取到的织物疵点边缘图像进行加权融合并优化处理.结果显示,该融合算法优于融合前两种单独使用的算法,能有效提取较连续、完整的织物疵点边缘特征,正检率为95.83%,较同类算法提高了1.98%.In order to solve the problems of low accuracy and efficiency in traditional manual detection of fabric defects,the classical Canny operator can not adapt to the selection of smoothing and adaptive threshold.In this paper,a fabric defect detection algorithm based on wavelet modulus maxima and adaptive Canny operator is proposed.The edge images of fabric defects extracted by adaptive Canny operator and wavelet modulus maxima algorithm are weighted and optimized.The results show that the fusion algorithm is superior to the two algorithms used before the fusion,and can effectively extract the continuous and complete edge features of fabric defects.The correct detection rate is 95.83%,which is 1.98%higher than the same algorithm.

关 键 词：疵点检测 自适应Canny算子 小波模极大值 图像融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]