Recognition of handwritten Hindu numerals using structural descriptors

Ashraf Elnagar, Saad Harous

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

A method for recognizing handwritten Hindi numerals is proposed based on the structural descriptors of a numeral's shape. The method consists of three major steps. The first one is preprocessing, where a handwritten numeral is scanned, normalized and then thinned. Next, a robust algorithm is used to segment the scanned image into stroke(s), based on feature points, and to identify cavity features. The output of this algorithm is a syntactic representation (that is one or more syntactic terms). Finally, this syntactic representation is matched against the set of prototype syntactic representations of handwritten numerals for a possible match. Early experimental results are not only encouraging but also proving the tolerance of the proposed system to recognize a high variability of Hindi numerals' shapes. The system attained a successful recognition rate of 96%.

Original languageEnglish
Pages (from-to)299-314
Number of pages16
JournalJournal of Experimental and Theoretical Artificial Intelligence
Volume15
Issue number3
DOIs
Publication statusPublished - Jul 2003
Externally publishedYes

Keywords

  • Handwritten recognition
  • Hindu numerals
  • Structural descriptors
  • Term rewriting

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Recognition of handwritten Hindu numerals using structural descriptors'. Together they form a unique fingerprint.

Cite this