A Projection Based Statistical Approach for Handwritten Character Recognition

Author

Pal, Sarbajit ; Mitra, Jhimli ; Ghose, Soumya ; Banerjee, Paromita

Author_Institution

VECC, Kolkata

Volume

2

fYear

2007

fDate

13-15 Dec. 2007

Firstpage

404

Lastpage

408

Abstract

The aim of this paper is to recognize upper-case English alphabets from handwritten documents. An OCR system based on four-sided projections of an alphabet is proposed. The projection points are approximated by polygons and feature points are extracted subsequently for notch elimination and segmentation of the polygon. The resulting segments are smoothed by Bezier approximation. Statistical matching technique is successfully applied for character recognition.

Keywords

document image processing; handwritten character recognition; image recognition; image segmentation; statistical analysis; Bezier approximation; OCR system; handwritten character recognition; handwritten documents; polygon segmentation; projection based statistical approach; statistical matching; upper-case English alphabets; Automation; Character recognition; Computational intelligence; Educational institutions; Feature extraction; Handwriting recognition; Hidden Markov models; Instruments; Optical character recognition software; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on

Conference_Location

Sivakasi, Tamil Nadu

Print_ISBN

0-7695-3050-8

Type

conf

DOI

10.1109/ICCIMA.2007.270

Filename

4426730