Discriminant parallel feature fusion based on maximum margin criterion for pattern classification

TitleDiscriminant parallel feature fusion based on maximum margin criterion for pattern classification
Publication TypeJournal Article
Year of Publication2008
AuthorsLi, J-B, Chu, S-C, Pan, J-S
JournalJournal of Digital Information Management
Volume6
Issue2
Pagination203 - 207
Date Published2008
KeywordsDiscriminant parallel feature fusion, Maximum margin criterion, Parallel feature fusion
Abstract

In this paper, we propose a novel parallel feature fusion based maximum margin criterion, namely discriminant parallel feature fusion, for pattern classification. The advantage of algorithm lies in: 1) A constrained optimization problem based on maximum margin criterion is created to solve the optimal fusion coefficients, which causes that fused data has the largest class discriminant in the fused feature space. 2) An unique solution of optimization problem is transformed to an eigenvalue problem, which causes the proposed fusion strategy to perform a consistent performance. Besides of the detailed theory derivation, many experimental evaluations also are presented in this paper.

URLhttp://www.scopus.com/inward/record.url?eid=2-s2.0-72449120326&partnerID=40&md5=45d5e7fee23074133279fb977574a551

Collaborative Partner

Institute of Electronic and Information Technology (IEIT)

Collaborative Partner

Collaborative Partner