Evaluation of a content-based image retrieval system using features based on colour means

In recent years, there has been an explosion in the use of digital photographic images in computers, especially since digital image creation facilities such as digital cameras, scanners, etc., are becoming increasingly popular. This development in digital photography has led to a huge collection of still images that are stored in digital format. As the demand for digital images increases, the need to store and retrieve images in an efficient manner arises. Therefore, the field of content-based image retrieval has emerged as an important research area in computer vision and image processing. The key issue in image retrieval is how to match two images according to computationally extracted features. Since speed and accuracy are important, we need to develop a system for retrieving images that is both efficient and effective. In this paper, we analyse one such content-based image retrieval system and test its suitability for building medical image databases. © 2012 Inderscience Enterprises Ltd.