Feature Integration, Multi-image Queries and Relevance Feedback in Image Retrieval

In this paper, we explore the effect of feature integration, multi-image queries, and relevance feedback in enhancing the performance of an image retrieval system. Weighted integration of structure, color and texture features is studied. In addition, we propose a methodology of retrieval consisting of multiple query images, as opposed to the traditionallyused model of a single query image. Two different mechanism of relevance feedback are also proposed and analyzed. Integration of features and feedback significantly improves the performance of the retrieval system.

[1]  Thomas M. Strat,et al.  Recognizing objects in a natural environment: a contextual vision system (CVS) , 1989 .

[2]  Alberto Del Bimbo,et al.  Visual image retrieval by elastic deformation of object sketches , 1994, Proceedings of 1994 IEEE Symposium on Visual Languages.

[3]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  A. Murat Tekalp,et al.  Integration of color, edge, shape, and texture features for automatic region-based image annotation and retrieval , 1998, J. Electronic Imaging.

[5]  Anil K. Jain,et al.  On image classification: city images vs. landscapes , 1998, Pattern Recognit..

[6]  Jake K. Aggarwal,et al.  Applying perceptual grouping to content-based image retrieval: building images , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[7]  Thomas S. Huang,et al.  Edge / Structural Features for Content Based Image Retrieval , 1999 .

[8]  Raimondo Schettini,et al.  Content-based color image retrieval with relevance feedback , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[9]  Lei Zhu,et al.  Supporting multi-example image queries in image databases , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

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

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

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

[13]  Yi Li,et al.  Consistent line clusters for building recognition in CBIR , 2002, Object recognition supported by user interaction for service robots.

[14]  Jake K. Aggarwal,et al.  Retrieval by classification of images containing large manmade objects using perceptual grouping , 2002, Pattern Recognit..

[15]  Jake K. Aggarwal,et al.  Combining structure, color and texture for image retrieval: A performance evaluation , 2002, Object recognition supported by user interaction for service robots.

[16]  Thomas S. Huang,et al.  Extending image retrieval with group-oriented interface , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[17]  Jake K. Aggarwal,et al.  CIRES: a system for content-based retrieval in digital image libraries , 2002, 7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002..

[18]  David P. Dobkin,et al.  A search engine for 3D models , 2003, TOGS.

[19]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.