A sparse representation method for image-based surface defect detection

作     者：YAO Ming-hai GU Qin-long 姚明海;顾勤龙

作者机构：College of Information Engineering Zhejiang University of Technology 

出 版 物：《Optoelectronics Letters》 (光电子快报（英文版）)

年 卷 期：2018年第14卷第6期

页      面：476-480页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：supported by the Zhejiang Provincial Natural Science Foundation of China(No.LZ14F030001) 

主　　题：surface defect detection A sparse representation method image-based 

摘      要：In this paper, an efficient sparse representation-based method is presented for detecting surface defects. The proposed method uses the sparse degree of coefficient in the redundant dictionary for checking whether the test image is defective or not, and the binary representation of the defective images is obtained, according to the global coefficient feature. Owing to the requirements for the efficiency and detecting quality, the block proximal gradient operator is introduced to speed up the online dictionary learning. Considering the correlation among the testing samples, prior knowledge is applied in the orthogonal-matching-pursuit sparse representation algorithm to improve the speed of sparse coding. Experimental results demonstrate that the proposed detection method can effectively detect and extract the defects of the surface images, and has broad applicability.