Handwritten digit recognition by a mixture of local principal component analysis

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journal

3 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)241-251
Journal / PublicationNeural Processing Letters
Volume8
Issue number3
Publication statusPublished - 1998
Externally publishedYes

Abstract

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. © 1998 Kluwer Academic Publishers.

Research Area(s)

  • Handwritten digit recognition, Mixture of principal component analysis, Neural networks

Citation Format(s)

Handwritten digit recognition by a mixture of local principal component analysis. / Zhang, Bailing; Fu, Minyue; Yan, Hong.

In: Neural Processing Letters, Vol. 8, No. 3, 1998, p. 241-251.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journal