基于稀疏优化的织物疵点检测算法  

Fabric defect detection algorithm based on sparse optimization

作　　者：刘洲峰[1] 闫磊[1] 李春雷[1] 董燕[1] 李阳[1] 

机构地区：[1]中原工学院电子信息学院,河南郑州451191

出　　处：《纺织学报》2016年第5期56-61,74,共7页Journal of Textile Research

基　　金：国家自然科学基金项目(61379113;61202499);河南省基础与前沿技术研究计划项目(142300410042);郑州市科技领军人才项目(131PLJRC643)

摘　　要：为提高稀疏表示方法对织物疵点的检测精度,提出了基于稀疏优化的织物疵点检测算法。首先,利用L1范数最小化从待检织物图像中学习出自适应字典库,用该库对织物图像稀疏表示,进而计算出稀疏表示系数矩阵;然后,对系数矩阵进行优化处理,采用字典库及优化系数矩阵对织物图像稀疏重构;最后,将重构图像与待检织物图像相减生成残差图像,用最大熵阈值方法对残差图像分割,定位出疵点区域。实验结果表明,本文算法所重构图像准确表示了正常织物纹理,相比已有检测方法具有较高的疵点检测精度。A novel fabric defect detection algorithm based on sparse optimization is proposed. Firstly,an adaptive dictionary is learned from test fabric image using L1-norm minimization method,the test fabric image is sparsely represented using the learned dictionary,and then the coefficient matrix of sparse representation is calculated. Secondly,the abnormal coefficients are removed using optimization function,then a new image is reconstructed using the optimized coefficient matrix and the dictionary. Finally,the reconstructed image is subtracted from original test image to acquire a residual image,and then the maximum entropy threshold method is used to segment the defect region. Experimental results demonstrate that the proposed algorithm has higher detection accuracy compared with the state of the art.

关 键 词：L1范数 稀疏表示 织物图像 疵点检测 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]