Classification of medical X-ray images using supervised and unsupervised learning approaches

Abstract

Most of the traditional approaches for medical image storage are least capable and scanning of relevant matching images are quite difficult. The existing approaches of content-based image retrieval (C-BIR) are less focused with medical images. The available research works with fuzzy logic approaches are very less and not efficient for medical image retrieval. Thus, there is a need of research work that can address both supervised and unsupervised learning approaches for medical image retrieval. Hence, the C-BIR technique is evolved with overcoming above stated concerns. Hence, this manuscript introduces two different C-BIR techniques using a support vector machine (SVM) and a fuzzy logic-based approach for classification. These approaches work on the classification based on feature extraction, region of Interest (ROI), corner detection, and similarity matching. The proposed approach has been analyzed for image retrieval for accuracy. The outcomes of the proposed study enhance the classification performances with retrieval than existing techniques of C-BIR.