基于图像处理的织物起毛起球分级研究  

Study on Fabric Pilling Classification Based on Image Processing

作　　者：董康乐 陈姗 安少元 高鑫 DONG Kangle;CHEN Shan;AN Shaoyuan;GAO Xin(Xi’an Polytechnic University,Xi’an 710048,China;Shaanxi Changling TextileMechanical&Electronic Technological Co.,Ltd.,Baoji 721013,China)

机构地区：[1]西安工程大学,西安710048 [2]陕西长岭纺织机电科技有限公司,陕西宝鸡721013

出　　处：《纺织器材》2019年第6期15-19,共5页Textile Accessories

摘　　要：为了对织物起毛起球等级做出客观、准确、定量的分析和评定,提出基于图像处理的织物起毛起球检测和分级方法;选用起毛起球织物样本验证起毛起球分级算法设计的有效性,设计制造起毛起球分级测试仪。起毛起球分级算法利用面阵CCD相机采集织物起毛起球图像,综合采用光照不均匀处理、图像均衡化、去噪、边缘检测等预处理方法,增强起毛起球图像信息;运用合适阈值二值化和形态学联合操作分割出起毛起球信息;以起毛起球面积比作为分级特征值实现分级。结果表明:该方法能有效滤除各种干扰信息,得到有效的起毛起球图像,实现1~5级织物起毛起球等级的准确评定。In order to make an objective,accurate and quantitative analysis and evaluation of the pilling grades of fabric,a method of pilling detection and classification based on image processing is proposed.Samples of pilling fabric are selected to verify the effectiveness of pilling grading algorithm design and a pilling grading tester is designed and manufactured.The pilling classification algorithm uses face array camera CCD to collect the pilling image of the fabric,and comprehensively adopts the pretreatment methods such as uneven illumination processing,image equalization,denoising and edge detection to enhance the pilling image information.Suitable threshold binarization and morphology are used to segment the pilling information.The pilling area ratio is used as the grading characteristic value.The results show that the method can effectively filter out all kinds of interference information,obtain effective pilling image,and realize accurate evaluation of pilling grade of grade 1~5 fabrics.

关 键 词：织物 起毛起球分级 图像处理 图像均衡化 边缘算子 漫水填充法 背景噪声 

分 类 号：TS103.63[轻工技术与工程—纺织工程]