Abstract

Diseases (Malady) have a serious impact on people’s life and health. Current research proposes an efficient approach to identify type of diseases in the human body based on the human fundus images. It is necessary to develop automatic methods in order to increase the accuracy of diagnosis for multiple type of maladies. In this system, multiple type diseases such as heart working, tumor, and etc disease could be identified by a new recognition method. Initially, images were preprocessed to remove noise and irrelevant background by filtering and transformation. The method of grey-level co- occurrence matrix (GLCM) was introduced to segment images of disease. Texture and color features of different disease images could be obtained accurately. Finally, by using the HNN (CNN+RNN) algorithm, multiple types of diseases were identified.

Key words: Fundus Image, Diagnosis of Malady, GLCM, Convolution Neural Network (CNN), Recurrent Neural Network (RNN)