International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 24 - Number 5 |
Year of Publication: 2011 |
Authors: Rahul Mehta, Nishchol Mishra, Sanjeev Sharma |
10.5120/2958-3910 |
Rahul Mehta, Nishchol Mishra, Sanjeev Sharma . Color - Texture based Image Retrieval System. International Journal of Computer Applications. 24, 5 ( June 2011), 24-29. DOI=10.5120/2958-3910
Content Based Image Retrieval (CBIR) is an interesting and most emerging field in the area of ‘Image Search’, in which similar images for the given query image searched from the image database. Current systems use color, texture and shape information for image retrieval. In this paper wepropose a method in which both color and texturefeatures of the images are used to improve the retrieval results in terms of its accuracy. Color extraction and comparison are performed using Conventionalcolor histograms (CCH) and the Quadratic Distance Metric (QDM)and the texture extraction and comparison are performed using the concept ofPyramid Structure Wavelet Transform Model (PSWTM) and the Euclidean distance. Color and texture based image retrieval computes image features more accurately whichare used to retrieve similar images from the database.