Proceedings. First Workshop on Document Image Analysis for Libraries

Abstract

Digital Libraries are becoming very important in our daily lives. This itself is a huge field that needs no introduction. On the other hand, document analysis and recognition is also a very well established field that deals with some distinctly different aspects of document processing. But in the broader picture of document storage and manipulation, these two communities are dealing with only part of the puzzle. In this paper, we present a commercial digital library that allows storage and manipulation of electronic documents. The novelty is that users can upload electronic documents in many formats, and the system automatically converts them to HTML documents so that they are immediately accessible using the standard web interface. The original layout and styles of the document is preserved in the HTML conversion process. The digital library then allows users to manipulate these documents in many ways. The Hawaii National Library has already installed the system and conducting large scale user testing.

Related Articles