ABSTRACT

Many modern scripts and languages can be traced back to various ancient scripts which evolved over the years to their present form and structure. These ancient texts provide significant insight into ancient history and civilization. But deciphering the ancient writings is a complex task as these writings are only available in form of inscriptions on rocks, caves, and palm leaves which are severely degraded due to environmental impact over several years. Preserving these texts and writings is of utmost importance. Digitization of the inscriptions can help in preservation and ease the sharing and searching of the text, like modern-day scripts and writings. Manual digitization is tedious and error-prone, so there is a need for an optical character recognition system for these ancient texts and scripts. Most of the modern-day scripts have various OCR systems implemented and these are in constant enhancement. The purpose of this study is to survey the OCR systems and techniques proposed for the various ancient scripts focusing on ancient Indian scripts.