基于局部纹理图像表征的织物疵点检测  

Fabric defect detection based on local texture image representation

作　　者：吴莹 郭佩瑶 刘燕萍 娄琳 王忍 WU Ying;GUO Peiyao;LIU Yan ping;LOU Lin;WANG Ren(School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China;School of Fashion Design&Engineering,Zhejiang Sci-Tech University,Hangzhou 310018,Zhejiang,China;School of Economics and Management,Zhejiang Sci-Tech University,Hangzhou 310018,Zhejiang,China)

机构地区：[1]天津大学电气自动化与信息工程学院,天津300072 [2]浙江理工大学服装学院,浙江杭州310018 [3]浙江理工大学经济管理学院,浙江杭州310018

出　　处：《东华大学学报（自然科学版）》2023年第6期73-79,共7页Journal of Donghua University(Natural Science)

基　　金：浙江省博士后科研择优资助项目(ZJ2022121);国家自然科学基金项目(52003245);浙江省自然科学基金项目(LQ18E030007)。

摘　　要：为实现织物纹理图像的自动表征与分析,提出一种基于局部纹理图像表征的织物疵点检测方法。根据纹理表征和疵点检测的不同应用,优化稀疏基数并优选子窗口尺寸。对于无疵点织物纹理表征,重叠子窗口可以提取更多纹理元素以便重构图像;对于疵点织物,无重叠子窗口划分可以减少样本数量,同时减少稀疏基数,提高检测效率。织物纹理表征选用8像素×8像素的子窗口尺寸,而织物疵点检测的子窗口尺寸为32像素×32像素。试验结果表明,重叠子窗口可以提取更多的纹理元素,在一定程度上抑制高斯噪声,从而得到高质量的重构图像。58张样本图像的疵点检出率为96.6%,证实所提算法对不同织物纹理和疵点类型有较好的适应性。In order to realize the automatic characterization and analysis of fabric texture images,a fabric defect detection method was proposed based on local texture image characterization.According to different applications of texture characterization and defect detection,the sparse cardinality and the sub window size were optimized.For the fabric texture without defects,overlapping sub windows can extract more texture elements to reconstruct the image.For defective fabrics,non overlapping sub window division can reduce the number of samples and the sparse cardinality,and improve the detection efficiency.The sub window size of 8 pixels and 8 pixels was selected for fabric texture characterization,while the sub window size of fabric defect detection was 32 pixels and 32 pixels.Experimental results show that overlapping sub windows can extract more texture elements,suppress Gaussian noise to a certain extent,so as to obtain high-quality reconstructed images.The defect detection rate of 58 sample images is 96.6%,which verifies that the algorithm has good adaptability to different fabric textures and defect types.

关 键 词：织物纹理 疵点检测 子窗口划分 表征 稀疏 

分 类 号：TS101.9[轻工技术与工程—纺织工程]