Handwritten digit recognition by a mixture of local principal component analysis

作     者：Zhang, BL Fu, MY Yan, H 

作者机构：Univ Sydney Dept Elect Engn Sydney NSW 2006 Australia Univ Newcastle Dept Elect & Comp Engn Newcastle NSW 2308 Australia 

出 版 物：《NEURAL PROCESSING LETTERS》 (神经处理通讯)

年 卷 期：1998年第8卷第3期

页      面：241-251页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：neural networks mixture of principal component analysis handwritten digit recognition 

摘      要：Mixture of local principal component analysis (PCA) has attracted attention due to a number of benefits over global PCA. The performance of a mixture model usually depends on the data partition and local linear fitting. In this paper, we propose a mixture model which has the properties of optimal data partition and robust local fitting. Data partition is realized by a soft competition algorithm called neural gas and robust local linear fitting is approached by a nonlinear extension of PCA learning algorithm. Based on this mixture model, we describe a modular classification scheme for handwritten digit recognition, in which each module or network models the manifold of one of ten digit classes. Experiments demonstrate a very high recognition rate.