Handwritten word recognition based on structural characteristics and lexical support

Author

Kavallieratou, E. ; Sgarbas, K. ; Fakotakis, N. ; Kokkinakis, G.

Author_Institution

Wire Commun. Lab., Patras Univ., Greece

fYear

2003

fDate

3-6 Aug. 2003

Firstpage

562

Abstract

In this paper a handwritten recognition algorithm based on structural characteristics, histograms and profiles, is presented. The well-known horizontal and vertical histograms are used, in combination with the newly introduced radial histogram, out-in radial and in-out radial profiles for representing 32 × 32 matrices of characters, as 280-dimension vectors. The recognition process has been supported by a lexical component based on dynamic acyclic FSAs (Finite-State-Automata).

Keywords

feature extraction; handwriting recognition; handwritten character recognition; image segmentation; acyclic FSA; dynamic FSA; feature extraction; feature vector; finite-state-automata; handwritten recognition algorithm; handwritten word recognition; horizontal histogram; in-out radial profile; lexical support; out-in radial profile; radial histogram; vertical histogram; Character recognition; Feature extraction; Handwriting recognition; Histograms; Humans; Image analysis; Image segmentation; Optical character recognition software; Text analysis; Wire;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on

Print_ISBN

0-7695-1960-1

Type

conf

DOI

10.1109/ICDAR.2003.1227727

Filename

1227727