计算机工程与应用2017，Vol.53Issue(18)：199-203,5.DOI:10.3778/j.issn.1002-8331.1603-0398
基于HOG和E-SVM的服装图像联合分割算法
Segmentation algorithm of clothing image based on HOG and E-SVM
摘要
Abstract
As the problem of the unsatisfied clothing segmentation accuracy, a novel segmentation algorithm is proposed based on HOG(Histogram of Oriented Gradients)features and E-SVM(Exemplar Support Vector Machine)classifiers. The co-segmentation algorithm can be divided into three steps:Superpixel grouping, E-SVM classifier training, segmentation propagation, which uses an auxiliary dataset. Firstly, user input image is segmented in superpixel, which makes the images in auxiliary dataset into regions. Secondly, some regions are selected to a positive segmentation, which uses HOG informa-tion to train E-SVM classifiers. Finally, the cloth is segmented in user image by E-SVM classifiers and segmentation prop-agation. Experimental results show that the proposed algorithm can segment clothing images with high accuracy.关键词
联合分割/方向梯度直方图(HOG)特征/超像素组合/模范支持向量机(E-SVM)分类器/分割传播Key words
co-segmentation/Histogram of Oriented Gradients(HOG)feature/superpixel grouping/Exemplar Support Vector Machine(E-SVM)classifier/segmentation propagation分类
信息技术与安全科学引用本文复制引用
黄冬艳,刘骊,付晓东,黄青松..基于HOG和E-SVM的服装图像联合分割算法[J].计算机工程与应用,2017,53(18):199-203,5.基金项目
国家自然科学基金(No.61462051,No.61462056,No.81360230,No.71161015) （No.61462051,No.61462056,No.81360230,No.71161015）
云南省应用研究基础计划面上项目(No.2014FB133) （No.2014FB133）
云南省应用研究基础重点项目(No.2014FA028) （No.2014FA028）
昆明理工大学自然科学研究基金(No.201403119). （No.201403119）
