creator Agam, Gad creator Frieder, Ophir The invention enables the digital management of large scale image databases, to efficiently classify and index image data independent of language. Complex processing requirements are required only on reduced and operably small subsets of the entire collection, thereby effectively scaling large document collections. Embodiments of the present invention provide image-based classification and retrieval of documents based on image recognition, e.g., signatures, logos, stamps, or word-spotting; in documents within real time for large datasets such as in the millions of documents. Submitted by Aric Ahrens (ahrens@iit.edu) on 2012-03-22T16:24:00Z No. of bitstreams: 1 7787711.pdf: 128207 bytes, checksum: e10c4be28ad49fdbdd7d6250a6a3a682 (MD5) Made available in DSpace on 2012-03-22T16:24:00Z (GMT). No. of bitstreams: 1 7787711.pdf: 128207 bytes, checksum: e10c4be28ad49fdbdd7d6250a6a3a682 (MD5) Previous issue date: 2010-08-31 Illinois Institute of Technology 2012-03-20 2010-08-31 7,787,711 http://hdl.handle.net/10560/2679 en United States Patent Patent reformatted digital application/pdf No Copyright - United States http://rightsstatements.org/page/NoC-US/1.0/ Open Access