Abstract
With the widespread of the network and development of Image technology, the older information retrieval techniques do not meet today’s demand. Recently, the content-based image retrieval has become the most developing topic and the techniques of content-based image retrieval have acquired great attention. In this paper, the basic components of content-based image retrieval system are discussed. Image retrieval methods based on color, texture, shape and semantic image are studied discussed and compared. Other related techniques such as relevance feedback and performance evaluation are also discussed. In the end of paper the problems and challenges are fetched out of each available technique. In recent areas of commerce, government, academics, and hospitals, large collections of digital images are being created and stored. Large amount of the digital image collections are the product of digitalizing existing collections of hardcopy photographs, diagrams, drawings, paintings, and prints. Usually, the only way of searching these collections was by keyword indexing, or simply by browsing related words. Digital image database however, open the way to content-based searching. In this paper we review some technical aspects of current content-based image retrieval systems.