Linear discriminant projection embedding based on patches alignment

作者：Wang, Jianzhong; Zhang, Baoxue^*; Qi, Miao; Kong, Jun

来源：Image and Vision Computing, 2010, 28(12): 1624-1636.

DOI：10.1016/j.imavis.2010.05.001

• Dimensionality reduction
• Manifold learning
• Patches alignment
• Face recognition
• Maximum margin criterion

Dimensionality reduction is often required as a preliminary stage in many data analysis applications. In this paper, we propose a novel supervised dimensionality reduction method, called linear discriminant projection embedding (LOPE), for pattern recognition. LOPE first chooses a set of overlapping patches which cover all data points using a minimum set cover algorithm with geodesic distance constraint. Then, principal component analysis (PCA) is applied on each patch to obtain the data's local representations. Finally, patches alignment technique combined with modified maximum margin criterion (MMC) is used to yield the discriminant global embedding. LOPE takes both label information and structure of manifold into account, thus it can maximize the dissimilarities between different classes and preserve data's intrinsic structures simultaneously. The efficiency of the proposed algorithm is demonstrated by extensive experiments using three standard face databases (ORL, YALE and CMU PIE). Experimental results show that LOPE outperforms other classical and state of art algorithms.

• 出版日期2010-12
• 单位东北师范大学