Content-Based Image Retrieval (CBIR) is an active area of research since the past decade. A lot of work is still being done in this area, which includes various applications such as security, medical imaging, audio and video retrieval. It shows the growing interest of many researchers in this field which results in new tools and techniques. This paper focuses on the key contributions of various researchers in the field of CBIR techniques. Then it discusses some literature gaps found in the adaptation of existing image retrieval techniques to build useful systems. It also includes the future scope of research in this field.

In recent years, there has been an exponential increase of the size of the so-called multimedia files. Everyday many gigabytes of visual information are generated. This is because of the substantial increase in affordable memory storage on the one hand and the wide spread usage of the world wide web (www) on the other hand. If there are no computer-aided browsing, searching and retrieving mechanisms to obtain the desired content, all this data is nearly useless. So, the need for an efficient tool to retrieve images from large datasets becomes crucial. This motivates the extensive research into image retrieval systems.

From the historical perspective, earlier, image retrieval systems used text-based search since the images are required to be annotated and indexed accordingly. However, with the substantial increase of the size of images as well as the size of image database, the task of text-based annotation becomes very cumbersome and tedious. At some extent, it is subjective and therefore incomplete. This is because the text often fails to convey the rich structure of the images. This motivates the research into what is referred to as Content-Based Image Retrieval (CBIR).

In CBIR system, the retrieval is based on (automated) matching of the features of the query image with those of the image database through some image-image similarity evaluation. Therefore, the images will be indexed according to their own visual content. The visual contents are the chosen features like color (distribution of color intensity across the image), texture (presence of visual patterns that have properties of homogeneity and do not result from the presence of single color or intensity), shape (boundaries, or the interiors of objects depicted in the image), or any other visual feature or a combination of a set of elementary visual features. We find the application of CBIR systems in many areas. The end users of such systems range from simple users searching a particular image on the web to various types of professional bodies from the government and private organizations, for example, the police force for picture recognition, journalists requesting pictures that match some query(ies) event(s), or engineers investigating a possible anomaly in system design try to find the right mapping of initial query images.

Information Technology Journal, Content-Based Image Retrieval, CBIR, Information Retrieval, Multimedia Files, World Wide Web, Datasets, Image Database, Visual Features, Picture Recognition, AltaVista Photo Finder, ALISA, Blobworld, RGB, HSV, Color Histogram.