款式特征描述符的服装图像细粒度分类方法-计算机辅助设计与图形学.PDFVIP

31 5 Vol.31 No.5 2019 5 Journal of Computer-Aided Design Computer Graphics May 2019 款式特征描述符的服装图像细粒度分类方法 1) 1,2)* 1,2) 1,2) 1,2) 吴苗苗 , 刘 骊 , 付晓东 , 刘利军 , 黄青松 1) ( 650500) 2) ( 650500) (kmust_mary@163.com) 摘 要: , , . ; HOG, LBP, 4 , ; 4 , SVM ; . , , , . 关键词: ; ; ; ; 中图法分类号: TP391.41 DOI: 10.3724/SP.J.1089.2019.17380 Fine-Grained Clothing Image Classification by Style Feature Description Wu Miaomiao1), Liu Li1,2)*, Fu Xiaodong1,2), Liu Lijun1,2), and Huang Qingsong1,2) 1) (Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500) 2) (Computer Technology Application Key Laboratory of Yunnan Province, Kunming 650500) Abstract: In order to solve the problem of unsatisfied accuracy with the simple styles of coarse-grained cloth- ing image classification, a fine-grained clothing image classification method by style feature description is proposed for various fashion women clothing. Firstly, the part-based detection was conducted to detect the un- classified images combing the training dataset of fashion women clothing. Secondly, four kinds of low-level features including HOG, LBP, color histogram, and edge operator of the training images and the unclassified clothing images after part-based detection were extracted, which can respectively obtain the images after fea- ture extraction. Then, the style feature descriptio