基于支持向量机的单面针织物组织结构的识别

Recognition of Single Knitted Fabric Structure Based on SVM

本文探索采用支持向量机的方法,对单面平针织物和集圈织物进行了结构识别。在对织物进行了数字图像采集和图像预处理后,提取了织物的覆盖率、垂直方向上纱线间隔大小的方差和纱线平均直径大小的方差,3个变量作为特征参数,建立了织物识别模型,实现了较高的识别率。

The method of support vector machine (SVM) was used to recognize the stitch structure of single plain and tuck knitted fabric in this paper. After getting and preprocessing the digital images of fabrics, fabric coverage rate, the variance of yarn intervals in the vertical direction and the variance of the yarn average diameters were selected as characteristic parameters of SVM, and recognizing model was established. The experiments showed that the method has good identification rate for single plain and tuck knitted fabric.