应用Gussian回代交替方向图像分解算法的色织物疵点检测  

Yarn-dyed fabric defect detection based on Gaussian back substitution image decomposition

作　　者：景军锋[1] 范晓婷[1] 李鹏飞[1] 张蕾[1] 张宏伟[1] 

机构地区：[1]西安工程大学电子信息学院,陕西西安710048

出　　处：《纺织学报》2016年第6期136-141,共6页Journal of Textile Research

基　　金：国家自然科学基金项目(61301276);西安工程大学博士科研启动基金资助项目(BS1416);西安工程大学学科建设经费资助项目(107090811)

摘　　要：针对传统的人工织物检测方法效率低,稳定性差,处理速度慢的问题,提出了基于Gaussian回代交替方向(ADMG)图像分解的色织物疵点检测算法。首先对疵点织物进行直方图均衡化的预处理操作,以减少织物背景纹理信息对织物疵点检测产生的影响。然后采用总方差范数与Sobolev空间中的半范数相结合的Gaussian回代交替方向的图像分解算法,将色织物图像分解为疵点部分u和纹理部分v。最后,应用二维Otsu阈值方法将图像的疵点部分u分割,识别织物图像上的疵点。实验结果表明:通过基于ADMG图像分解算法对包括星型、方格型和圆点型在内的色织物图像疵点检测是可行、有效的,可得到满意的识别结果。Focusing on the problems of low detection efficiency,poor stability and slow processing speed of conventional artificial fabric detection,a Yarn-dyed fabric defect detection method based on alternating direction method with Gaussian back substitution（ ADMG） image decomposition was presented. Firstly,histogram equalization as preprocessing was first conducted for the sampled images to eliminate the influence of background texture of fabric defects. Secondly,ADMG image decomposition method based on the combination of the total variation norm and semi-norm in negative Sobolev space was employed,and the Yarn-dyed fabric images could be decomposed into defect structure u and texture structure v.Finally,the defect structure u was segmented by using a two-dimensional Otsu thresholding,and the fabric defects could be identified. The experimental results demonstrate that method based on ADMG image decomposition is feasible and effective in Yarn-dyed fabric defect detection contained star-,boxand dot- Yarn-dyed fabric images and satisfactory identification results could be achieved.

关 键 词：图像分解 织物疵点检测 总方差范数 Gaussian回代交替方向法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]