Character Recognition System for Modi Script

Optical character recognition (OCR) is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-generated text. Character recognition is one of the oldest fields of research since the advent of computers. Till now OCR has been developed for several languages like English, Devnagari (Hindi), Bangla etc. But not much work has been done for Modi script. Modi script has been used in Maharashtra in the 17th century, Modi script was widely used in Maharashtra for writing up to 1950 and contained lot of literature of various philosophers and has its own historical importance. And to convert that literature into computer readable format using optical character recognition systems is our objective. Hence the proposed system will be beneficial for extracting the literature from Modi script. This project work elaborates algorithm required for Modi script OCR. After initial stage of Segmentation, we have used Affine Moment Invariants for calculating moments of each character. These moments were used for training of the system and building database. Thereafter classification has been performed using Fuzzy Logic.