Research And Implementation On Content-Based Image Retrieval

Content Based Image Retrieval (CBIR) is a technique for retrieving image on the basis of automatically-derived vision feature, it has been an active research area in recent year; CBIR is a fuzzy inquiry technology in fact.The issue involves three aspects:the extraction of characteristics, characteristic match, and the relevant feedback.and chosen suitable algorithm, designed a CBIR system.In image character ,mainly discussed extract optesthesia information such as colour color, edge, and texture feature from images. It has color histogram; Tamura texture feature and fourier description.In character macth, having discussed Euler distance, histogram distance and so on.In relevant feedback,having discussed the inquiry vector optimization algorithm.The method of retrieving JPEG compressed images was proposed. The features were extracted directly in DCT compressed domain, using the characterization of DCT. Instead of fully decompressing JPEG images, Therefore, the work of retrieving images is accelerated. Also, the efficiency of retrieving is satisfied, with certain robustness.