Target Search Techniques for Content-Based Image Retrieval Systems

Content-based image retrieval (CBIR) has received much research interest since couple of decades. In CBIR systems, searching of a desired image from multimedia database is known as target search process. The techniques which are available today are having slow convergence rate and they also not guarantee to search desired image. To overcome these disadvantages, four new methods are proposed. It is observed that these four methods are able to search the desired image accurately with fast convergence rate. The experimental results show that the iterations required to search the desired image are reduced considerably. Index Terms—Content-Based Image Retrieval (CBIR), Slow Convergence and Target Search.

[1]  Sharad Mehrotra,et al.  Evaluating refined queries in top-k retrieval systems , 2004, IEEE Transactions on Knowledge and Data Engineering.

[2]  Wai Lok Woo,et al.  A review of content-based image retrieval , 2010, 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010).

[3]  Dragutin Petkovic,et al.  Query by Image and Video Content: The QBIC System , 1995, Computer.

[4]  Ingemar J. Cox,et al.  The Bayesian image retrieval system, PicHunter: theory, implementation, and psychophysical experiments , 2000, IEEE Trans. Image Process..

[5]  Michael R. Lyu,et al.  An Empirical Study on Large-Scale Content-Based Image Retrieval , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[6]  Stevan Rudinac,et al.  Global Image Search vs. Regional Search in CBIR Systems , 2007, Eighth International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS '07).

[7]  Agma J. M. Traina,et al.  Fighting the Semantic Gap on CBIR Systems through New Relevance Feedback Techniques , 2006, 19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06).