An Intelligent Decision Support System for Retinal Disease Diagnosis based on SVM using a Smartphone

초록

This paper proposes a decision support system to recognizing retinal diseases. This paper uses a smartphone platform and cloud computing as the base of the system. A microscopic lens is attached into the smartphone camera to capture the user retinal image for recognizing the user’s retinal condition. An application is assembled in computer and then installed in to the smartphone. The application role is to connect between the system in smartphone and system in cloud, the application will send the retinal image to the cloud system to be classified. The paper uses OCFE (optimized classifier based on feature elimination) algorithm as the classifier. The retinal image is trained using combination of two ophthalmology databases DIARETDB1 v2.1 and STARE. Therefore, this system average accuracy is 88%, while the average error rate is 12%.

키워드