Optical Character Recognition (OCR) for Kannada numerals using Left Bottom 1/4th segment minimum features extraction

In this paper an algorithm to OpticalCharacter Recognition (OCR) for Kannadanumerals is discussed. The novelty exists insegmentation of the numeral into four equal partsand using one of these parts i.e., left bottomsegment to extract recognition features. Thealgorithm also proposes a single conflict resolutiontechnique to resolve conflicts while conflictingfeatures are encountered. A minimum number offeatures are extracted by the algorithm so as toimprove the response time