Hybrid off-line OCR for isolated handwritten Greek characters

  • Authors:
  • G. Vamvakas;B. Gatos;I. Pratikakis;N. Stamatopoulos;A. Roniotis;S. J. Perantonis

  • Affiliations:
  • Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research "Demokritos", Athens, Greece and Department of Informatics and Telec ...;Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research "Demokritos", Athens, Greece;Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research "Demokritos", Athens, Greece;Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research "Demokritos", Athens, Greece and Department of Informatics and Telec ...;Department of Informatics and Telecommunications, University of Athens, Greece;Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research "Demokritos", Athens, Greece

  • Venue:
  • SPPR'07 Proceedings of the Fourth conference on IASTED International Conference: Signal Processing, Pattern Recognition, and Applications
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we present an off-line OCR methodology for isolated handwritten Greek characters mainly based on a robust hybrid feature extraction scheme. First, image pre-processing is performed in order to normalize the character images as well as to correct character slant. At the next step, two types of features are combined in a hybrid fashion. The first one divides the character image into a set of zones and calculates the density of the character pixels in each zone. In the second type of features, the area that is formed from the projections of the upper and lower as well as of the left and right character profiles is calculated. For the classification step Support Vectors Machines (SVM) are used. The performance of the proposed methodology is demonstrated after testing with the CIL database (handwritten Greek character database), which was created from 100 different writers.