Flexible non-greedy discriminant subspace feature extraction. (August 2019)

• Record Type: Journal Article
• Authors: Zhao, Henghao; Fu, Liyong; Gao, Zhigang; Ye, Qiaolin; Yang, Zhangjing; Yang, Xubing
• Is Part Of: Neural networks. Volume 116(2019)
• Page Start: 166
• Page End: 177
• Publication Date: 2019-08
• Subjects: L1-norm-based non-greedy discriminant analysis -- Lp-norm inter-class dispersion -- Intra-class dispersion -- Robust distance measurement; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2019.04.006
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Recently, L 1 -norm-based non-greedy linear discriminant analysis (NLDA-L 1 ) for feature extraction has been shown to be effective for dimensionality reduction, which obtains projection vectors by a non-greedy algorithm. However, it usually acquires unsatisfactory performances due to the utilization of L 1 -norm distance measurement. Therefore, in this brief paper, we propose a flexible non-greedy discriminant subspace feature extraction method, which is an extension of NLDA-L 1 by maximizing the ratio of L p -norm inter-class dispersion to intra-class dispersion. Besides, we put forward a powerful iterative algorithm to solve the resulted objective function and also conduct theoretical analysis on the algorithm. Finally, experimental results on image databases show the effectiveness of our method