CBIR system for biomedical images: challenges and open issues

The aim of CBIR is to retrieve similar images from a large image database efficiently. There is large number of images generated by hospitals and clinics every day. These images play very important role in diagnosis of diseases, medical research and education. These images demand highly effective techniques for processing and organizing. One of the techniques in this direction is content-based image retrieval for finding similar images from an image archive. Characteristics of medical images differ significantly from other general-purpose images and hence require special treatment. In this paper, we have explained the general CBIR system for large medical databases and discussed the challenges specific to this area along with the open issues.