A Model-Based Segmentation Method for Handwritten Numeral Strings

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

8 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)383-403
Journal / PublicationComputer Vision and Image Understanding
Volume70
Issue number3
Publication statusPublished - Jun 1998
Externally publishedYes

Abstract

Segmentation of handwritten touching characters is an important task in optical character recognition (OCR). A new model-based segmentation algorithm is proposed for handwritten numeral strings. This method is based on the boundary analysis of the numeral strings, where a set of new features are extracted. These features can be used for global interpretation of the boundary structures. Various models are then constructed for the common touching patterns, which can increase the reliability of the segmentation and reduce the segmentation time. While we concentrate on the description of the segmentation method for two single-touching digits in this paper, our method can be extended to segmentation of touching digits in other situations. © 1998 Academic Press.

Research Area(s)

  • Character segmentation, Contour analysis, Handwritten character recognition, Structural method, Touching numeral strings