Abstract—Many techniques have been reported for handwritten based document image retrieval. This paper proposes a method by using Contourlet Transform (CT) for feature extraction of document images which achieves high retrieval rate. The handwriting of different people is often visually distinctive; we take a global approach based on texture analysis, where each writer’s handwriting is regarded as a different texture. The distance measures viz., Canberra distance and Euclidean distances are used as similarity in proposed system. Superiority of Canberra distance is observed over Euclidean distance in term of average retrieval rate. Retrieval results with proposed method are very promising with precisions and recalls.
Index Terms—Document image analysis and retrieval, Contourlet Transform, document similarity measurement, handwritten documents, handwriting classification and retrieval, writer identification.
M. S. Shirdhonkar is with the Dept. of Computer Science and Engineering, B. L. D. E. A‟s College of Engineering and Technology, Bijapur, India (e-mail: ms_shirdhonkar@rediffmail.com)
Manesh B. Kokare is with the Dept. of Electronics and Telecommunication, S. G. G. S, Institute of Engineering and Technology, Nanded, India ( e-mail: mbkokare@sggs.ac.in)
Cite: M. S. Shirdhonkar and Manesh B. Kokare, "Handwritten Document Image Retrieval," International Journal of Modeling and Optimization vol. 2, no. 6, pp. 693-696, 2012.
Copyright © 2008-2024. International Journal of Modeling and Optimization. All rights reserved.
E-mail: ijmo@iacsitp.com