Algorithm to Identify Kannada Vowels using Minimum Features Extraction Method
K.S. Prasanna Kumar
Prof. K.S. Prasanna Kumar, PG, Department of Computer Science, Acharya Institute of Technology, Bangalore, India.
Manuscript received on 09 January 2013 | Revised Manuscript received on 18 January 2013 | Manuscript Published on 30 January 2013 | PP: 79-84 | Volume-2 Issue-2, January 2013 | Retrieval Number: B0381012213 /2013©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper introduces a novel way of feature extraction for Optical Character Recognition (OCR) customized for Kannada characters. The algorithm described here relies on breaking the character into four equal parts and using one of the quarters for extraction. The algorithm is deliberately kept away from all the complexities and the number of features to be extracted is also minimized so as to increase the efficiency and speed of recognition. The algorithm also describes a conflict resolution technique helpful in effectively utilizing the algorithm.
Keywords: Kannada OCR, Minimal Feature Extraction, Character recognition Algorithm, Conflict resolution.
Scope of the Article: Algorithm Engineering