Document Type



Media is loading

Publication Date



In this digital era, our communication has evolved and the use of “hard copy” documents including historical documents has been changed throughout the years. However, preserving these cultural-historic documents protects our heritage, preserves our legacy, and ultimately, saves our past for generations to come. Several conservation treatments require documents to be stored physically flat in a cool, dry, and dark area (avoiding exposure from light) inside acid-free, alkaline materials (like boxes, folders, or mats) or in polyester film folders. Although attempts to preserve records in their original format are obvious, it is also necessary to make such historical documents in readable formats. In general, conventional information systems use to digitize old documents that are limited to storage. Storage, however, is not complete digitization. Therefore, in our study, we propose to utilize image analysis and computer vision techniques (mostly for document image analysis [1]) to extract information (texts and graphics) so it is possible to sparse data in accordance with the structure of the documents. We will provide encouraging qualitative results on few documents.

First Advisor

KC Santosh

Research Area

Computer Science, Mathematics