IMAGE RETRIEVAL USING COLOUR, SHAPE AND TEXTURE

Abstract

Content-based Image Retrieval (CBM) has become one of the most active. research areas in the past few years. It is a fundamental operation in machine vision and a key step in object. recognition. With the increasing popularity of the use of large volume image databases in various applications like medicine, entertainment, education, manufacturing etc. it becomes imperative to build an automatic and efficient retrieval system to browse through the entire database. Techniques being used currently are limited in their applications. Most of the attention from the research has been focused on indexing techniques based on single image feature that exploit visual cue such as colour, shape or texture. The use of single image attribute may lack sufficient discriminatory information and, might not be able to support large variations in image attributes. The techniques in use currently based on, methods exploiting shape do not take. colour or texture content of image into account. Some techniques are based On colour but. these lack discriminatory information as far as shape or texture content of _images is concerned. So techniques are being developed which combine the colour, shape and texture attributes as in human perception of images. In this dissertation work experiments on integration of colour and shape features and integration of colour and texture features are done. Colour, shape and texture features are computed using colour histograms, edge length histograms or gradient projections and local, energy of wavelet coefficients respectively.