A Clustering Approach to Image Retrieval Using Range Based Query and Mahalanobis Distance

This chapter puts forward a new approach to address a general purpose Content-Based Image Retrieval(CBIR) task. Six spatial color moments extracted from visually significant locations of an image are used as features to characterize an image. It utilizes information given by a set of queries, as opposed to a single image query. A set of similar images is posed as a query and Mahalanobis distance is used to evaluate the similarity between query images and target images of the database. Given a query set, the mean and covariance for computing Mahalanobis distance is obtained from the same. Unlike conventional CBIR methods in which images are retrieved based on considering similarities between the query image and the database images through a sequential search, a clustering technique using K-means algorithm is first used to create meaningful groups in the database. As clusters are created by considering similarities between images in the database, the image retrieval search space is reduced if clusters near to the query are searched. The effectiveness of the proposed algorithm is demonstrated with increased accuracy and reduced retrieval time.