A Kannada Document Image Retrieval System based on Correlation Method.

Abstract

The present growth of digitization of books and manuscripts demands an immediate solution to access them electronically. This requires research in the area of document image understanding, specifically in the area of document image retrieval. There is an immense scope for such a retrieval system for a digital library of Kannada Document Images. This paper presents an efficient Content Based Document Image Retrieval system for a Kannada document image collection. A recognition-free approach is followed because recognition based approach is inefficient in terms of performance. The data is pre-processed and segmented for faster matching and retrieval. An efficient search technique - Correlation method is used to search in large collection of document images. Performance evaluation using different datasets of Kannada documents shows the effectiveness of the approach