Image Retrieval Based On Color And Texture

Content-Based Image Retrieval (CBIR) is a popular technique in the field of image processing. CBIR extracts visual features as the retrieval features, such as color, texture, shape etc. Generally, features of the example image needed are extracted firstly, and then compared with the features of other images in the database. After the result is showed to the user.Based on research in relative field including detailed analysis of CBIR architecture, features extraction methods and image match technique, two methods are proposed in this paper.We combined two techniques of based on chromaticity moments technique and statistical distribution of wavelet transformation coefficients for content-based image retrieval(CBIR).First,only a small number of features, called chromaticity moments, are required to capture the spectral content (chrominance) of an image. Only a small fixed number of compact features need to be stored to effectively characterize the color content of an image. Secondly, the wavelet coefficients provide important directional information ,the statistics of image wavelet coefficients is generalized Gaussian distribution. This approach forms the feature vector of the image by taking advantage of the statistical distribution of wavelet transformation coefficients .Experimental result show that an efficient image retrieval method based on chromaticity moments technique and statistical distribution of wavelet transformation coefficients.The approaches use the Local Binary Pattern (LBP) texture feature as the source of image description.This paper presents an improved LBP histogram spatially enhanced LBP (SEL) histogram with spatial information by dividing the LBP labeled images into k×k regions.We compare the method of SEL and the method of dynamic regions matching. As shown in the experimental results, the method of SEL is better than the whole of LBP method.When similituded matching, we introduce Dynamic Partial distance Function (DPF)into dynamic regions matching.As a whole the tetrieval precision will be more advanced.