作者: Jinrong Cui , Jiajun Wen , Zizhu Fan
DOI: 10.1007/S11042-014-1887-4
关键词: Sample (statistics) 、 Artificial intelligence 、 Weighting 、 Pattern recognition (psychology) 、 Expression (mathematics) 、 Class (biology) 、 Computer science 、 Representation (mathematics) 、 Pattern recognition 、 Computer vision 、 Feature (machine learning) 、 Media Technology 、 Computer Networks and Communications 、 Hardware and Architecture 、 Software
摘要: The palmprint recognition methods can be categorized as the feature-based and appearance-based methods. conventional representation merely express test sample a weighting sum of training samples exploit deviation between from each class for classification. In this paper we exploited an method called bidirectional based pattern classification (BRBPC) on recognition. BRBPC algorithm not only used to sample, but also take into account expression sample. Experiments PolyU multi-spectral database 2D 3D show that proposed outperforms