计算机图像处理技术在鞋服款式识别中的应用研究  

Application of Computer Image Processing Technology in Pattern Recognition of Shoes and Clothing

作　　者：宋凯利 韦华 SONG Kaili;WEI Hua(Xi'an Aeronautical Polytechnic Institute,Xi'an 710089,China)

机构地区：[1]西安航空职业技术学院,陕西西安710089

出　　处：《中国皮革》2024年第8期135-138,142,共5页China Leather

基　　金：西安航空职业技术学院项目(22XHJG29);陕西省中华职教社项目(ZJS202334)。

摘　　要：本文旨在探索一种基于鞋服轮廓形状特征的款式识别方法,针对当前研究中存在的主要难点问题,提出了相应的解决方案。在计算机图像处理技术的概念和应用场景的理论基础上,介绍了一种基于边缘检测和形态学操作的鞋服图像预处理算法,该算法能够有效分割出鞋服轮廓,并消除噪声和细节干扰。同时,提出了一种基于傅里叶描述子的轮廓特征提取方法,有效描述鞋服轮廓的形状特征,并利用支持向量机(Support Vector Machine,SVM)进行轮廓特征的分类。This paper aimed to explore a style recognition method based on the outline shape features of shoes and clothing,and put forward corresponding solutions for the main difficulties in the current research.Based on the con⁃cept of computer image processing technology and the theory of application scene,an image preprocessing algorithm based on edge detection and morphology operation was introduced.The algorithm can segment the outline of shoes and clothing effectively and eliminate the noise and detail interference.At the same time,a method of contour feature ex⁃traction based on Fourier descriptors was proposed,which can effectively describe the shape features of the outline of shoes and clothing,and use support vector machine(SVM)to classify the contour features.

关 键 词：款式识别 计算机图像处理 SVM 傅里叶描述子 

分 类 号：TS56[轻工技术与工程—皮革化学与工程]