Reducing User Log size in an Inter-Query Learning Content Based Image Retrieval (CBIR) System with a Cluster Merging approach

Use of relevance feedback (RF) in the feature vector model has been one of the most popular approaches to fine tune query for content-based image retrieval (CBIR) systems. This paper proposes a framework that extends the RF approach to capture the inter-query relationship between current and previous queries. By using the feature vector model, this approach avoids the need of "memorizing" actual retrieval relationship between the actual image indexes and the previous queries. This implies that the approach is more suitable for image database application where images are frequently added and removed. The proposed inter-query relationship is presented using a data cluster that is defined by a transformation matrix, a centroid point and the reference boundary value. These parameters are captured in a file commonly known as the user log. The file however will grow rapidly after successive retrieval sessions. In order to reduce the size of the user log, this paper introduces a merging approach to combine clusters that are close-by and similar in their characteristics. Experiments have shown that the proposed framework has out performed the short term learning approach and yet without the burden of the complex database maintenance strategies required in long-term learning approach.

[1]  Kok Wai Wong,et al.  A Feature Selection Framework for Small Sampling Data in Content-based Image Retrieval System , 2005, 2005 5th International Conference on Information Communications & Signal Processing.

[2]  Markus A. Stricker,et al.  Similarity of color images , 1995, Electronic Imaging.

[3]  Qionghai Dai,et al.  Multilayer semantic representation learning for image retrieval , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[4]  Thomas S. Huang,et al.  Small sample learning during multimedia retrieval using BiasMap , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Matthieu Cord,et al.  Semantic kernel updating for content-based image retrieval , 2004, IEEE Sixth International Symposium on Multimedia Software Engineering.

[6]  Douglas R. Heisterkamp.  Building a latent semantic index of an image database from patterns of relevance feedback , 2002, Object recognition supported by user interaction for service robots.

[7]  Matthieu Cord,et al.  Semantic kernel learning for interactive image retrieval , 2005, IEEE International Conference on Image Processing 2005.

[8]  Ramin Zabih,et al.  Comparing images using color coherence vectors , 1997, MULTIMEDIA '96.

[9]  Thomas S. Huang,et al.  Comparing discriminating transformations and SVM for learning during multimedia retrieval , 2001, MULTIMEDIA '01.

[10]  Thomas S. Huang,et al.  Edge-based structural features for content-based image retrieval , 2001, Pattern Recognit. Lett..

[11]  Ramesh Jain,et al.  Storage and Retrieval for Image and Video Databases III , 1995 .

[12]  Lei Wang,et al.  A criterion for optimizing kernel parameters in KBDA for image retrieval , 2005, IEEE Trans. Syst. Man Cybern. Part B.

[13]  Edward Y. Chang,et al.  Support vector machine active learning for image retrieval , 2001, MULTIMEDIA '01.

[14]  King Ngi Ngan,et al.  A memory learning framework for effective image retrieval , 2005, IEEE Transactions on Image Processing.

[15]  Wei-Ying Ma,et al.  Learning a semantic space from user's relevance feedback for image retrieval , 2003, IEEE Trans. Circuits Syst. Video Technol..

[16]  Christopher J. C. Burges,et al.  Simplified Support Vector Decision Rules , 1996, ICML.

[17]  Chee Sun Won,et al.  Efficient use of local edge histogram descriptor , 2000, MULTIMEDIA '00.

[18]  Matthieu Cord,et al.  Long-term similarity learning in content-based image retrieval , 2002, Proceedings. International Conference on Image Processing.

[19]  Mingjing Li,et al.  A statistical correlation model for image retrieval , 2001, MULTIMEDIA '01.

[20]  Mingjing Li,et al.  Statistical correlation analysis in image retrieval , 2002, Pattern Recognit..

[21]  Douglas R. Heisterkamp,et al.  Summarizing inter-query learning in content-based image retrieval via incremental semantic clustering , 2004, International Conference on Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004..

[22]  Jorma Laaksonen,et al.  Using Long-Term Learning to Improve Efficiency of Content-Based Image Retrieval , 2003, PRIS.

[23]  Jing Peng,et al.  Improving the Initial Image Retrieval Set by Inter-Query Learning with One-Class SVMs , 2003 .

[24]  Bir Bhanu,et al.  Improving retrieval performance by long-term relevance information , 2002, Object recognition supported by user interaction for service robots.

[25]  Thomas S. Huang,et al.  Relevance feedback in image retrieval: A comprehensive review , 2003, Multimedia Systems.

[26]  Chi-Hang Chan,et al.  Using Biased Support Vector Machine to Improve Retrieval Result in Image Retrieval with Self-organizing Map , 2004, ICONIP.

[27]  Michael R. Lyu,et al.  A novel log-based relevance feedback technique in content-based image retrieval , 2004, MULTIMEDIA '04.

[28]  Lei Guo,et al.  A memorization learning model for image retrieval , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[29]  Ivor W. Tsang,et al.  The pre-image problem in kernel methods , 2003, IEEE Transactions on Neural Networks.