International Journal of Applied Engineering Research ISSN 0973-4562 Volume 9, Number 24 (2014) pp. 28533-28546 © Research India Publications http://www.ripublication.com Paper code: 29956 IJAER An Image Retrieval by Content of the Image using Color, Texture and Shape Purohit Shrinivasacharya 1* and Dr. M. V. Sudhamani 2 1* Department of Information Science and Engineering Siddaganga Institute of Technology, Tumkur, 572103, India Email: purohitsn@gmail.com 2 Department of Information Science and Engineering R. N. S. Institute of Technology, Bangalore, 560098, India Email: mvsudha_raj@hotmail.com Abstract As per the recent survey, it is noticed that image storage and retrieval on the World Wide Web (WWW) has made significant progress. The present searching systems have still confronts for us while searching the images from the web. In this paper, a new idea to extract the images from the image database is presented to achieve better performance. The proposed CBIR system is implemented by considering the low level visual features of an image. The low level features are obtained by converting the color image into a grayscale image. The color features are obtained using modified Block Truncation Coding (BTC) method. The four statistical properties (energy, contrast, entropy and uniformity) of the texture extracted as a second low level features. The third visual property of image is extracted as shape feature using shape descriptor. Finally, an experiment is conducted on the ground truth image database that has more than 1000 images of different categories. In our previous work a middle range of block size has given best performance as color features. A block size of 32 x 32 is chosen for the experiment to enhance the performance of the system. The proposed system performance has been improved by combining these three features. Keywords: World Wide Web, BTC, Color, Texture, Shape, Database. Introduction The image data in the web is growing very fast in the present day because of social