A Study of Telugu Script Recognition Schemes

Abstract

As the world moves close to the concept of the soft office, communication and storage of documents is performed digitally. Documents and files that were once stored on paper are now being converted into electronic form in order to facilitate faster trappings, searches, and modifications, as well as to extend the life of such records. Acountless portion of business documents and communication still takes place in physical form and the fax machine remains a vital tool of communication worldwide. Hence, there is a great demand for a system, which robotically extracts, analyzes, and stores information from hardcopies for later repossession. All of these tasks fall under the general heading of document analysis, which has been a fast growing area of research in recent years. A very significant area in the arena of document analysis is that of optical character identification(OCR), which is broadly defined as the process of recognizing text from document images and converting it into electronic form. To date, many algorithms have been presented in the literature to handle this task for a particular language, and these OCRs will not work for a document comprising more than one language. In this paper a brief discussion of five of these algorithms for specifically Telugu script recognition is presented.