色纺纱线中纤维混色比例的图像检测  

Image inspection of fiber blending percentages in colored spun yarns

作　　者：沈利利[1] 李忠健[1] 潘如如[1] 卢雨正[1] 高卫东[1] 唐佩君[2] 

机构地区：[1]生态纺织教育部重点实验室(江南大学),江苏无锡214122 [2]百隆东方股份有限公司,宁波浙江315201

出　　处：《纺织学报》2016年第3期138-143,共6页Journal of Textile Research

基　　金：教育部博士点基金项目(20120093130001);江苏省产学研前瞻性研究项目(BY2013015-20);霍英东教育基金资助项目(141071)

摘　　要：为解决色纺纱线中有色纤维配比的经验性及耗时性等问题,在结合视频显微镜和图像处理技术的基础上,提出一种基于聚类算法的色纤维颜色分类及比例测定方法。首先将色纺纱线解捻获得色纤维,在轻微张力下排列在载玻片上,利用视频显微镜进行图像采集;然后采用灰度投影方法定位色纤维,再提取出每根纤维中心线上的像素点,分别取所有像素点的R、G、B分量的平均值构成特征向量来表征该根纤维;最后将RGB模型的特征向量转换到L*a*b*模型并通过聚类算法对色纤维进行分类,确定图像中各颜色纤维所占比例。实验表明,本文算法能够实现色纺纱线中色纤维种类的确定及比例测定。In order to solve the problems of the empirical spadework and time consuming when confirming the proportions of the colored fibers in the colored spun yarns,with the help of the video microscopy and image processing technology,a novel method based on a clustering algorithm is proposed to classify the color fibers and inspect the proportions of different color fibers. Firstly,the colored spun yarns are untwisted into the fibers,the colored fibers are arranged on the slide under the mild tension,and the corresponding images are captured by the video microscopy. Secondly,the gray projection method is adopted to localize the colored fibers,and the average value of R,G,B of all pixels in the center line of each colored fiber is extracted as a feature vector to characterize the colored fiber respectively. Finally,the feature vectors in RGB model are converted to the L＊a＊b＊color model,a clustering algorithm by searching density peaks is applied into classifying the colored fibers and the proportions of each color fibers are calculated. Experiments results demonstrate that the proposed method can inspect the colors and proportions of colored fibers in the colored spun yarns with a satisfactory accuracy.

关 键 词：色纤维 颜色分类 图像处理 聚类算法 

分 类 号：TS101.9[轻工技术与工程—纺织工程]