Content based image retrival using invariant color and texture features

Abstract: Content Based Image Retrieval (CBIR) techniques appeared in 1990s. It uses low-level features like color, texture and shape to describe image content, and breaks through the limitation of traditional text query technique. This project we are proposes an image retrieval method based on color-feature and texture-feature similarity score. Many methods can be used to describe color feature. In this project we will use color moment method because it has the lowest feature vector dimensions and lower computational complexity. The HSV color space is describes a specific color by it’s hue, saturation, and brightness values. For the similarity measurement the first order mean, the second standard deviation, and the third skewness color moments have been provided to be efficient and effective in representing color distribution of images. In this paper, the retrieval results from color feature and texture feature are analyzed, furthermore texture can be through as repeated patterns of pixel over a spatial domain. Since there is no mathematical definition for texture, many different methods are proposed for computing texture. Here we are used different distance based similarity measurement methods are proposed, before we are doing texture features apply ranklet transform can be calculated at different resolutions using Haar wavelet supports.

Keywords: Smart antenna; wireless mobile network; adaptive antenna; broadcast scheduling.