Content-based image retrieval (CBIR) is a method which uses visual contents to seek images from large size image databases according to the choice of the users. Human intervention in the text based image retrieval makes the system cumbersome, labor intensive and time consuming. Hence, there is a need to design the algorithms to retrieve the desired images from the database without human intervention, to enable for fast, accurate and reliable retrieval of the desired images. The challenge of the CBIR system is to identify the suitable features of images to retrieve image from image database. The algorithm presented in this paper uses color, texture and shape features to form the feature vector of training images and test images. These feature vectors and the k-NN classifier is used to search the test image in the database of training images. A database of 2732 fruit images from six different classes is used to test the proposed algorithm. The higher recognition accuracy achieved for the proposed algorithm is 98.43%.

CBIR, k-NN, Color, RGB, Texture, Entropy, Shape, Eccentricity

[1] S. K. Chang, and A. Hsu, "Image information systems: where do we go from here?" IEEE Trans. On Knowledge and Data Engineering, Volume – 05, Issue - 05, Page No. (431-442), 1992.
[2] H. Tamura, and N.Yokoya, "Image database systems: A survey", Pattern Recognition, Volume – 17, Issue - 01, Page No. (29-43), 1984.
[3] Ritendra Datta, Dhiraj Joshi, Jia Li and James Z., Wang, “Image Retrieval : Ideas, Influences and Trends of the New Age”, ACM Computing Surveys, Volume – 40, Issue - 02, Article 5, 2008.
[4] W. Niblack, R. Barber, “The QBIC project: Querying Images by Content using Color, Texture and Shape”, Storage and Retrieval for Image and Video Databases I, 1908, SPIE Proceedings Series, Feb. 1993.
[5] Pentland, R. W. Picard, S. Sclaroff, “Photobook: Tools for Content Based Manipulation of Image Databases”, Storage and Retrieval for Image and Video Databases II, 2185, SPIE Proceedings Series, Feb. 1994.
[6] Y. Gond, H. Zhang, “An Image Database System with Content Capturing and Fast Image Indexing Abilities”, IEEE International Conference on Multimedia Computing and Systems, Page No. (121-130), May 1994.
[7] Rajivkumar S. Mente, Basavraj V. Dhandra, Guraraj Mukarambi, “Color Based Information Retrieval”, International. Journal of Advances Computer Engineering and Architecture, Volume – 01, Issue – 02, Page No. (271-280), 2011.
[8] Flickner, Sawhney, Niblack, Ashley, Huang, Dom, Gorkani, Hafner, Lee, Petkovic, Steele, Yanker, “Query by Image and Video Content: The QBIC System”, IEEE RFC 2460, Volume – 28, Issue – 09, Page No. (23-32), 1995.
[9] Coggins, J. M., “A Framework for Texture Analysis Based on Spatial Filtering,” Ph.D. Thesis, Computer Science Department, Michigan State University, East Lansing, Michigan, 1982.
[10] Tamura, H., S. Mori, and Y. Yamawaki, “Textural Features Corresponding to Visual Perception,” IEEE Transactions on Systems, Man, and Cybernetics, SMC-8, Page No. (460-473), 1978.
[11] Sklansky, J., “Image Segmentation and Feature Extraction,” IEEE Transactions on Systems, Man, and Cybernetics, SMC-8, Page No. (237-247), 1978.
[12] Haralick, R.M., “Statistical and Structural Approaches to Texture,” Proceedings of the IEEE, Volume - 67, Page No. (786-804), 1979.