Web Document Image Retrieval System Based on Word Spotting

Nowadays, the huge non-indexing quantities of image archives (especially document images) require the development of intelligent tools for their retrieval with convenience comparable of the texts search engines. The proposed technique addresses the document retrieval problem by a word matching procedure. It performs matching directly in the images bypassing OCR and using word-images as queries. It is constituted of two different parts: The offline and the online operation. In the offline operation, the archive of document images is examined and the results are stored in a database. The online operation consists of the Web interface, the creation of the word´s image and finally, the matching stage. The proposed matching process it can be described shortly as a two-threshold rating system. Finally, the proposed system has been build and it can be found in at the Web address: http://orpheus.ee.duth.gr/irs2.