Abstract

In today’s real life applications complexity of multimedia contents is significantly increased. This is highly demanding the development of effective retrieval systems to satisfy human desires. Recently, extensive research efforts have been carried out in the field of content-based image retrieval (CBIR). These research efforts are based on various parameters; feature extraction (to find content of image), similarity matching (compare the content of a query image with content of other images), indexing (index images based on their content), and relevance feedback (consider users view to get better output). The efforts result many promising solutions in designing effective and interactive CBIR systems. This paper mainly includes study of some recent CBIR techniques with the goal to design efficient system. Additionally, this study presents a detailed framework of CBIR system. Further it includes improvements achieved in the major areas like feature extraction, indexing, similarity matching, relevance feedback.