Abstract

There is rapid increase in image databases of remote sensing images due to image satellites with high resolution, commercial applications of remote sensing & high available bandwidth in last few years. The problem of content-based image retrieval (CBIR) of remotely sensed images presents a major challenge not only because of the surprisingly increasing volume of images acquired from a wide range of sensors but also because of the complexity of images themselves. In this paper, a software system for content-based retrieval of remote sensing images using RGB and HSV color spaces is presented. Further, we also compare our results with spatiogram based content retrieval which integrates spatial information along with color histogram. Experimental results show that the integration of spatial information in color improves the image analysis of remote sensing data. In general, retrievals in HSV color space showed better performance than in RGB color space.

Authors

Bikesh Kumar Singh¹, G.R. Sinha², Bidyut Mazumdar³
National Institute of Technology, Raipur (C.G.), India¹, Shri Shankaracharya College of Engineering and Technology, India², National Institute of Technology, Raipur (C.G.), India³

Keywords

Content Based Image Retrieval, RGB, HSV, Spatiograms