Optical Character Recognition Techniques for Restoration of Thai Historical Documents

Abstract

Historical documents are national treasures. Insignificant effort has been made to restore Thai historical documents. Other nations such as Egypt, China, Greece, and USA are investing a large effort in restoring and preserving their national historical documents. This study is towards creating a framework that is directed towards digitally restoring Thai historical document. As a starting point, the focus is on using one Thai historical document for performing experiments and verifying OCR methods available in this research area. We also present our approach in resolving one of the main issues in all historical documents - broken characters.