Arabic text recognition using steady state genetic algorithm

Abdullah M. Al-Mutawa, Chilukuri K. Mohan

Research output: Contribution to journalArticlepeer-review


Text recognition is a challenging task when text contains overlapping and cursive characters. This paper addresses the task of matching input Arabic text with character forms in the database described in terms of features. We introduce new features that approximate character shapes, designed to make the recognition process independent of font size. We apply steady state genetic algorithms to the partial shape-matching task, with extremely encouraging recognition rate. No separate segmentation is required in our approach.

Original languageEnglish (US)
Pages (from-to)311-316
Number of pages6
JournalIntelligent Engineering Systems Through Artificial Neural Networks
StatePublished - 1998
Externally publishedYes


  • Character Recognition
  • Edge Detection
  • Feature Extraction
  • Genetic Algorithms

ASJC Scopus subject areas

  • Software


Dive into the research topics of 'Arabic text recognition using steady state genetic algorithm'. Together they form a unique fingerprint.

Cite this