电子测量与仪器学报

刘秀平,冯奇,袁皓,徐健,陆珍,王圣鹏,闫焕营.LBP与低秩分解的网状织物纹理缺陷检测方法[J].电子测量与仪器学报,2021,35(1):135-141

LBP与低秩分解的网状织物纹理缺陷检测方法

Defect detection of mesh fabric with LBP and low rank decomposition

DOI：

英文关键词:LBP fabric texture feature extraction low rank decomposition defect detection

基金项目:陕西省科技厅项目(2018GY 173)、西安市科技局项目(GXYD75)资助

作者	单位
刘秀平	西安工程大学电子信息学院西安710048
冯奇	西安工程大学电子信息学院西安710048
袁皓	西安工程大学电子信息学院西安710048
徐健	西安工程大学电子信息学院西安710048
陆珍	西安工程大学电子信息学院西安710048
王圣鹏	西安工程大学电子信息学院西安710048
闫焕营	深圳罗博泰尔机器人有限公司深圳518109

Author	Institution
Liu Xiuping	School of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
Feng Qi	School of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
Yuan Hao	School of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
Xu Jian	School of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
Lu Zhen	School of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
Wang Shengpeng	School of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
Yan Huanying	Shenzhen Municipal Robotel Robot Technology Co., LTD, Shenzhen 518109, China

摘要点击次数: 1076

全文下载次数: 3

中文摘要:

针对网状织物纹理复杂,缺陷检测难度大的问题,提出一种基于局部二值模式(LBP)与低秩稀疏矩阵分解的网状织物纹理缺陷检测方法.首先,采用等价旋转不变的局部二值模式算法提取网状织物纹理特征,获得纹理特征矩阵;其次,根据纹理特征矩阵构建低秩稀疏分解模型;最后,通过最佳阈值分割算法对网状织物低秩稀疏分解产生的显著图进行分割.实验结果表明,与K 奇异值分解（K SVD）算法相比,该方法的平均准确率达到8994%,平均召回率达到9388%,分类总正确率达到92%以上。

英文摘要:

For the problem of complex texture and difficulty in defect detection of mesh fabric. An algorithm based on local binary pattern (LBP) and low rank sparse matrix decomposition for defect detection of mesh fabric is proposed. Firstly, the local binary pattern with equivalent invariant rotation is used to extract the features of the mesh fabric image, and the texture feature matrix is obtained. Then, an appropriate low rank sparse decomposition model is constructed based on the texture feature matrix. Finally, the significant graph generated by sparse matrix was segmented by OTSU optimal threshold segmentation algorithm, so that the defects of mesh fabric could be detected. Compared with K SVD algorithm, the experimental results show that the average accuracy of the method in this paper is 8994%, the average recall rate is over 9388%, and the total accuracy of classification is over 92%.

查看全文查看/发表评论下载PDF阅读器