Multi-resolution classification trees in OCR design

Author

Brun, Marcel ; Barrera, Jorge ; Hirata, Nina S T ; Trepode, Nestor W. ; Dantas, Daniel ; Terada, Routo

Author_Institution

Inst. de Matematica e Estatistica, Sao Paulo Univ., Brazil

fYear

2001

fDate

37165

Firstpage

59

Lastpage

66

Abstract

The paper recalls the idea of classification trees in OCR (optical character recognition) systems and proposes a technique for the automatic design of these classification trees. The design of both the classification trees and of the classification operators are based on training from sample pairs of observed-ideal images, allowing the development of customized OCRs

Keywords

mathematical morphology; optical character recognition; pattern classification; tree data structures; trees (mathematics); OCR design; automatic design; classification operators; customized OCRs; morphological multi-classifier; multi-resolution classification trees; observed-ideal images; optical character recognition systems; Character generation; Character recognition; Classification tree analysis; Consumer electronics; Optical character recognition software; Optical design; Optical design techniques; Optical filters; Optical materials; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Graphics and Image Processing, 2001 Proceedings of XIV Brazilian Symposium on

Conference_Location

Florianopolis

Print_ISBN

0-7695-1330-1

Type

conf

DOI

10.1109/SIBGRAPI.2001.963038

Filename

963038