一种机织物密度图像分析系统的研究与应用  

Research and application of the image analysis system for woven fabric density

作　　者：潘全 殷正雄 何瑜[3] PAN Quan;YIN Zhengxiong;HE Yu(Hubei Province Fibre Inspection Bureau,Wuhan 430061,Hubei,China;Wuhan Miaowei Technology Co.,Ltd.,Wuhan 430074,Hubei,China;College of Chemistry and Chemical Engineering,Hubei University,Wuhan 430062,Hubei,China)

机构地区：[1]湖北省纤维检验局,湖北武汉430061 [2]武汉妙微科技有限公司,湖北武汉430074 [3]湖北大学化学与化工学院,湖北武汉430062

出　　处：《纺织检测与标准》2022年第5期18-21,共4页Textile Testing and Standard

基　　金：国家市场监督管理总局科技计划项目(2020MK063)资助。

摘　　要：为了解决传统机织物密度测试过程中存在的检测效率低、人工误差大等问题,研究了一种机织物密度图像分析系统。该系统通过图像采集装置获取织物样本高清图像,利用图像分析平台算法模块中的自动聚焦算法和自动分割算法对采集的图像进行标定、经纬向分割以及角度矫正,由试验结果管理模块计算标准单位长度内对应的经纬向根数,完成织物密度试验结果的自动输出。与传统人工测量相比,图像分析系统的检测结果相对偏差小于5%,这表明该系统具有较高的实际应用价值。In order to solve the problems of low detection efficiency and human error in the traditional woven fabric density detection,a kind of image analysis system for woven fabric density was developed.The high-definition image of fabric samples was obtained through the image acquisition device,and by using the automatic focusing and automatic segmentation algorithm in the algorithm module of the image analysis platform,the collected image was calibrated,the warp and weft was segmented and the angle was corrected.The corresponding number of warp and weft yarns in the standard unit length were calculated by the test result management module,and the automatic output of fabric density test results completed.Compared with the traditional manual measurement,the relative deviation of the detection results of the image analysis system was less than 5%.The results showed this system had high practical application value.

关 键 词：机织物 织物密度 图像分析 自动聚焦算法 自动分割算法 

分 类 号：TS101.9[轻工技术与工程—纺织工程]