A Literature Survey of Image Descriptors in Content Based Image Retrieval

Abstract

As a result of the new communication technologies and the massive use of Internet in the society, the amount of audio-visual information available in digital format is increasing considerably. This has necessitated designing systems that allow describing the content of several types of multimedia information in order to search and classify them. The audio visual descriptors are used for contents description in Content Based Image Retrieval (CBIR). The CBIR is a technique for retrieving images on the basis of automatically-derived features such as color, texture and shape. It uses digital processing and analysis to automatically generate descriptions directly from the media data. Image descriptors are the descriptions of the visual features of the contents in images, which describe elementary characteristics of images such as the shape, the color, the texture or the motion, among others. A literature survey study is most important for understanding and gaining insight about specific area of a subject. Therefore, in this paper we survey some of the state-of-art technical aspects of image descriptors in CBIR. Even though lots of research works had been published on CBIR, however, in this paper an effort has been made to explore an in-depth chronological growth in this field of image descriptors with respect to performance measure metrics of CBIR systems.