基于滚动引导滤波与FT算法的色织物疵点检测  

Defect Detection of Yarn-dyed Fabric Based on Rolling Guide Filtering and FT Sailiency

作　　者：王晨煜 景军锋[1] 张缓缓[1] 苏泽斌 WANG Chenyu;JING Junfeng;ZHANG Huanhuan;SU Zebin(Xi′an Polytechnic University,Shaanxi Xi′an,710600)

机构地区：[1]西安工程大学

出　　处：《棉纺织技术》2019年第6期28-33,共6页Cotton Textile Technology

基　　金：国家自然科学基金(61301276);陕西省重点研发计划(2017GY-003);陕西省高校科协青年人才托举计划项目(20180115);陕西省教育厅科研计划项目资助(18JK0338)

摘　　要：针对色织物疵点检测纹理背景对检测结果影响大的问题,提出一种滚动引导滤波和频率调谐显著性相结合的色织物疵点检测算法。采用滚动引导滤波在保留疵点区域的同时抑制色织物的纹理背景;应用频率调谐视觉显著性算法得到全分辨率的显著图;使用迭代阈值分割将显著图二值化,并运用形态学运算去除孤立的像素点,疵点检测效果较好。认为:该算法能够有效抑制织物的纹理,对疵点区域精准分割。Aimed at the problem of texture background greatly affecting the defect testing results for yarn dyed fabric,a detection algorithmic for yarn dyed fabric with outstanding combinate between rolling guide filtering and frequency tuned were put forward.The rolling guide filtering was adopted to keep defect area meanwhile restrain the texture background of yarn dyed fabric.The saliency map of full resolution ratio was obtained with the algorithm by applying frequency to tune the visual significance.The binarization of saliency map was performed with the iteration threshold segmentation.The morphological algorithm was applied to remove isolated pixel.The defect detection effects were better.It is considered that the algorithmic can efficiently restrain the fabric texture and divide the defect area accurately.

关 键 词：疵点检测 纹理抑制 滚动引导滤波 频率调谐显著性 色织物 

分 类 号：TS101[轻工技术与工程—纺织工程] TP391[轻工技术与工程—纺织科学与工程]