Automated Recognition of Handwritten Malayalam Scripts

Optical Character Recognition(OCR) is the process of translation of images of typewritten or handwritten text into machine encoded text. Recently Indian Handwritten Character Recognition is getting much more attention and researchers are contributing a lot in this field. But Malayalam, a South Indian language has very less works in this area and needs further attention. This book focuses on an efficient algorithm for recognizing the handwritten Malayalam characters. It consists of basically 15 vowels and 37 consonants. The existence of lot of their combinations and connected characters, the recognition poses a gargantuan challenge in front of us. Malayalam OCR is a complex task owing to the various character scripts available and more importantly the difference in ways in which the characters are written. The method illustrated is tested with different documents written by 508 different persons of various fields. The data selection concentrated to cover almost all categories of people like children, youngsters, working class etc. It is tested for different sets of samples ranging 11490 letters in the 1276 different documents and an accuracy of 96% is achieved.