In this paper,a semi-supervised dimensionality reduction algorithm for feature extraction,named LRDPSSDR,is proposed by combining local reconstruction with dissimilarity preserving.It focuses on local and global struc...
详细信息
In this paper,a semi-supervised dimensionality reduction algorithm for feature extraction,named LRDPSSDR,is proposed by combining local reconstruction with dissimilarity preserving.It focuses on local and global structure based on labeled and unlabeled samples in learning process.It sets the edge weights of adjacency graph by minimizing the local reconstruction error and preserves local geometric structure of samples.Besides,the dissimilarity between samples is represented by maximizing global scatter matrix so that the global manifold structure can be preserved well.Comprehensive comparison and extensive experiments demonstrate the effectiveness of LRDPSSDR.
In order to find a set of optimal discriminant vectors which can maximize the inter-class scatter while simultaneously minimizing the intra-class scatter after the projection,a new algorithm of orthogonal optimal disc...
详细信息
ISBN:
(纸本)9781538629185
In order to find a set of optimal discriminant vectors which can maximize the inter-class scatter while simultaneously minimizing the intra-class scatter after the projection,a new algorithm of orthogonal optimal discriminant vectors and a new algorithm of statistically uncorrelated optimal discriminant vectors for feature extraction were proposed.Compared with the original MMC feature extraction method,the new feature extraction method greatly eliminates the statistical correlation between the best discriminant vectors and improves the recognition rate.The experiment results on Olivetti Research Laboratory(ORL)face database shows that the new feature extraction method of statistically uncorrelated maximum margin criterion(SUMMC)are better in terms of recognition rate and stability.Besides,the relation between maximum margin criterion and Fisher criterion for feature extraction were revealed.
暂无评论