International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 22 - Number 4 |
Year of Publication: 2011 |
Authors: Nirase Fathima Abubacker, Indra Gandhi Raman |
10.5120/2571-3534 |
Nirase Fathima Abubacker, Indra Gandhi Raman . An Approach for Structural Feature Extraction for Distorted Tamil Character Recognition. International Journal of Computer Applications. 22, 4 ( May 2011), 24-28. DOI=10.5120/2571-3534
Feature extraction is an important task for designing an OCR for recognizing degraded documents. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Shape inconsistency among characters of the same structure is sometimes quite large because of the poor resources and environmental impact on the document images. Therefore, it is necessary to select features which can adapt to the shape variations irrespective of the distortions. Hence, in this paper, selection of appropriate standard structural features is taken as the primary task for various distortion types that are considered to recognize the Tamil distorted characters