The Influence of Local Descriptors on Content Based Image Retrieval Systems for Building Recognition

In this paper we will present our experiments regarding Content Based Image Retrieval for a public database of images containing buildings. We have based our research on the possible improvements brought by splitting the image into regions and computing a certain descriptor for each one of these. Our goal was to observe the influence of local descriptors on buildings recognition. Experimental tests performed on a public database of images containing buildings showed that the proposed approach provides significant improvements in the retrieval performance, compared to the global descriptors.

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

[2]  Jing Huang,et al.  Spatial Color Indexing and Applications , 2004, International Journal of Computer Vision.

[3]  Wan-Chi Siu,et al.  Multimedia Information Retrieval and Management , 2003 .

[4]  Luc Van Gool,et al.  HPAT Indexing for Fast Object/Scene Recognition Based on Local Appearance , 2003, CIVR.

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

[6]  Simone Santini,et al.  Exploratory Image Databases: Content-Based Retrieval , 2001 .

[7]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[8]  Ramin Zabih,et al.  Histogram refinement for content-based image retrieval , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[9]  Shengjiu Wang.  A Robust CBIR Approach Using Local Color Histograms , 2001 .

[10]  Markus A. Stricker,et al.  Color indexing with weak spatial constraints , 1996, Electronic Imaging.

[11]  Marcel Worring,et al.  Content-Based Image Retrieval at the End of the Early Years , 2000, IEEE Trans. Pattern Anal. Mach. Intell..