Myanmar Handwritten Recognition and Erratum Detection by using MICR

Abstract

This paper contribute recognition and detection erratum for Myanmar handwritten compound words. MICR (Myanmar Intelligent Character Recognition) is used for the character recognition. Because this method is interesting algorithm to recognize Myanmar characters that has been developed recently in Myanmar. It contains statistical, semantic and the final decision is made by the voting system. Erratum Detection, it is a new contribution of detecting compound word in string texts. It dependent on the language set of string substitutions reflects the surface form of errors that result from cognitive, typographical mistakes, or mistyping. A robust erratum detection technique is needed to cover above all situation. The system index pair possible extended/medial code and then provides a pair code for detect complete compound word. In detection, it has three situations: twice the same extended, extended/medials pair not matching error and not compound word in real. The final output, Myanmar compound words will be produced editable text with highlight in each error word.