Research of Image Retrieval Algorithms Based on Color

With the explosion of multimedia data, the traditional image retrieval method by text couldn't meet people's demand of more accurate retrieval results any longer. Therefore, the content-based image retrieval (CBIR) has been researched to achieve more accurate results. CBIR uses image visual features to represent image and perform retrieval. Color feature is applied most widely in image retrieval systems. In this paper, we choose several common CBIR algorithms based on color to analyze their robustness to the characteristics of images. We test 9 kinds of images for the algorithms. From the experiment performance, we evaluate the adaptability of the algorithms under different kinds of images.

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

[2]  James Ze Wang,et al.  Image retrieval: Ideas, influences, and trends of the new age , 2008, CSUR.

[3]  A. Conchon,et al.  Applications and services , 2001 .

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

[5]  Shih-Fu Chang,et al.  Image Retrieval: Current Techniques, Promising Directions, and Open Issues , 1999, J. Vis. Commun. Image Represent..

[6]  Peter J. L. van Beek,et al.  Image retrieval using blob histograms , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[7]  Raj Acharya,et al.  Color Space Quantization for Color-Content-Based Query Systems , 2004, Multimedia Tools and Applications.

[8]  Constantine Stephanidis,et al.  Universal Access in Human-Computer Interaction , 2011 .

[9]  Clement T. Yu,et al.  Techniques and Systems for Image and Video Retrieval , 1999, IEEE Trans. Knowl. Data Eng..

[10]  Qian Yin,et al.  Combining Color and Shape Features for Image Retrieval , 2009, HCI.