Improving the Sinhala Handwritten Word Recognition Using a Dictionary with Consonant and Vowel Information Extraction

Abstract

Sinhala language is used by Sinhalese, the major ethnic group native to Sri Lanka, that comprise the majority of the population (75%) in the country. Most of the textual data gathered in Sri Lanka is in the Sinhala language. The written paper documents in Sinhala is converted to electronic format requires an enormous amount of human labour. If the conversion can be automated using handwriting recognition, it would increase efficiency and a significant cost can be saved. In most of the researches the characters are segmented and recognized. Many applications require identifying words rather than individual character modifier combinations. When the identified characters are put together to create a word, if the characters are not identified correctly from the character recognition algorithm, the word as a whole is going to be incorrectly identified. In this research, a method to improve the recognition rates using a dictionary, consonant and vowel information is used. The recognition rate could be improved from 63% to 79%.