DIABETES DETECTION USING PARTICLE SWARM OPTIMIZATION IN TONGUE IMAGES

摘要

Abstract: Medical Imaging is a scientific procedure of creating nonlinguistic representations of the interior of a body for clinical analysis. It seeks to expose internal structures hidden by the skin and bones, as well as to diagnose and treat the disease. It also provides a database of normal anatomy and physiology to make it possible to determine abnormalities. It is observed to set aside a set of techniques that non-invasively produce images of the internal perspective of the body Diabetic Retinopathy (DR) is a complexity of Diabetes Mellitus (DM) that can cause blindness. To attack this advancing endemic, this paper proposes a non-mvasive method to detect DM at an early stage based on the physiognomy extracted from tongue images. Tongue analysis is one of the prominent area to diagnose most of the diseases. The tongue is a muscular organ used to utter, smack and ingest the food. The objective of the organ extends to identify the internal working of a human body. Any unpredictable response of the human body parts such as stomach, pancreas, liver and intestines will revert on the tongue. The changes in the tongue ensures the dereliction of the internal organs of the human being. The changes could be inspected by the difference in the color and surface of the tongue. In this paper, processing of tongue image by employing Particle Swarm Opt.mization (PSO) is contemplated. The segmented study of the tongue reflects the presence of diabetes in a person; in addition optimization technique is used to obta.n the best result. The system framework involves obtaining the image, . alluring of the image, identifying the texture and color feature and finally classified as normal or diabetic.