Discriminant sparse locality preserving projection for face recognition

详细信息    查看全文

• 作者：Yifang Yang ; Yuping Wang ; Xingsi Xue
• 关键词：Dimensionality reduction ; Sparse representation ; Feature extraction ; Manifold learning
• 刊名：Multimedia Tools and Applications
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：76
• 期：2
• 页码：2697-2712
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems; Computer Communication Networks; Data Structures, Cryptology and Information Theory; Special Purpose and Application-Based Systems;
• 出版者：Springer US
• ISSN：1573-7721
• 卷排序：76

文摘

In this paper, aiming at the drawback of the popular dimensionality reduction method Discriminant Sparse Neighborhood Preserving Embedding(DSNPE), i.e. the construction of its between-class scatter is too complexity, a novel algorithm Discriminant Locality Preserving Projection (DSLPP) is proposed. Our proposal retains the local sparse reconstructive relationships of DSNPE and constructs a novel between-class scatter by using all mean faces as sparse representation dictionary. In particular, DSLPP preserves the sparse reconstructive relationship of mean face, so then it can not only efficiently reduce the between-class scatter computation complexity of DSNPE, but also increase the discriminant power. In the experiment, we compare DSLPP with classic and state-of-the-art dimensionality reduction methods on the publicly available data sets such as ORL, Yale, UMIST, and AR, and further apply the Gabor feature into DSLPP on AR face database to further improve its performance. The experimental results show that DSLPP is able to obtain a better representation of the class information and achieve much higher recognition accuracy.