MARGIN AND DOMAIN INTEGRATED CLASSIFICATION FOR IMAGES

作     者：YEN-LUN CHEN YUAN F. ZHENG YI LIU 

作者机构：Center for Intelligent and Biomimetic Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 P. R. China Department of Electrical and Computer Engineering The Ohio State University Columbus OH 43210 USA PIPS Technology A Federal Signal Company Knoxville TN 37932 USA 

出 版 物：《International Journal of Information Acquisition》 

年 卷 期：2011年第8卷第1期

页      面：1-16页

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Margin and domain integrated classification (MDIC) pattern classification multi-category classification support vector machine (SVM) support vector domain description (SVDD) 

摘      要：Multi-category classification is an ongoing research topic in image acquisition and processing for numerous applications. In this paper, a novel approach called margin and domain integrated classifier (MDIC) is addressed. It merges the conventional support vector machine (SVM) and support vector domain description (SVDD) classifiers, and handles multi-class problems as a combination of several target classes plus outliers. The basic idea behind the proposed approach is that target classes possess structured characteristics while outliers scatter around in the feature space. In our approach, the domain description and large-margin discrimination are adjustable and therefore yield higher classification accuracy which leads to better performance than conventional classifiers. The properties of MDIC are analyzed and the performance comparisons using synthetic and real data are presented.