|Project Description: ||The area of content-based image retrieval is a hybrid research area that requires knowledge of both computer vision and of database systems. Users are exploiting the opportunity to access remotely-stored images in all kinds of new and exciting ways. However, this has exacerbated the problem of locating a desired image in a large and varied collection. This has led to the rise of a new research and development field known as content-based image retrieval (CBIR), the retrieval of images on the basis of features automatically extracted from the images themselves.
Content-based retrieval systems utilize measures that are based on low-level attributes of teh image itself, including color histograms, color composition, and texture. State-of-the-art research focuses on the more powerful measures that can find regions of an image corresponding to known objects that users wish to retrieve.
Our research was focus on a unified methodology for the feature representation and object class recognition. The aim of this project was to develop an image retrieval method that utilizes the layout and the structure of the perceptually correct color within an image to measure the similarity of images. The developed methodology can be used as automatic indexing capabilities for large image databases.