Image retrieval using colour features

With the significant outgrowth of hardware technology, the amount of pictorialinformation has increased remarkably. Due to this increase in image data, the need for anefficient indexing technology arises.In earlier retrieval systems, images are described using plain text and retrieval isbased on the text description using conventional information retrieval techniques. Thesesystems are good for retrieval abstract concepts captured in images. However, it suffersthe problem of subjectiveness and manual entry of text description.To overcome these limitations content-based retrieval techniques using imagefeatures have been proposed. The main features used for image retrieval are shape,texture and colour.The purpose of our work is to develop an efficient content-based retrievaltechnique based on colour. Researchs on colour feature have shown very successfulresults. However, these techniques have been applied to the overall image content. Theprocessing time for extracting colour features is another problem. In this paper, wepropose three extensions to the basic colour histogram matching technique: (a) the use ofhue value of HSI colour space; (b) the use of segmentation for object level; and (c) theuse of clustering