Medical Image Retrieval Using Multiple Features Clustering Technique

A mass of medical images are generated for diagnosis some unfamiliar diseases. Pathology researches and medical education require searching similar images from database in order to improve the quality and efficiency of care process. It is an imperative to build an efficient retrieval system to browse through the entire data base. To over come the draw backs of the existing systems we proposed new and effective image retrieval scheme by integrating clustering and feature extraction. In proposed technique images are clustered by improved mountain clustering technique texture and shape features are extracted using steerable filter and pseudo-zernike movements. Experimental results show that the proposed approach improves the retrieval performance than the retrieval systems based on the individual features.