AbstractsCommunication

A great challenge in the biomedical engineering is the non-invasive assessment of the physiological changes occurring inside the human body. Specifically, detecting the abnormalities in the human eye is extremely difficult due to the various complexities associated with the process. Retina is the significant part of the human eye which can reflect the abnormal changes in the human eye. Hence, retinal images captured by digital cameras can be used to identify the nature of the abnormalities affecting the human eye. Retinal image analysis has gained sufficient importance in the research arena due to the necessity for disease identification techniques. Abnormality detection using these techniques is highly complex since these diseases affect the human eye gradually. Conventional disease identification techniques from retinal images are mostly dependent on manual intervention. Since human observation is highly prone to error, the success rate of these techniques is quite low. Since treatment planning varies for different abnormalities, the accuracy of the identification techniques must be significantly high. Lack of accuracy in these techniques may lead to fatal results due to wrong treatment. Hence, there is a significant necessity for automation techniques with high accuracy for retinal disease identification applications. Several automation techniques have been reported in the literature for retinal image analysis. Most of these techniques are computational algorithms which require the usage of computers to a high extent. These computational algorithms can be broadly divided into two categories: (a) Artificial Intelligence (AI) based techniques and (b) Non-AI techniques.%%%References p. 136-149, List of Publications p. 150-153