International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 175 - Number 35 |
Year of Publication: 2020 |
Authors: O.O Obe, Olotuah Adedolapo Fisayo |
10.5120/ijca2020920903 |
O.O Obe, Olotuah Adedolapo Fisayo . Iris Nevus Disease Diagnosis using Convolutional Neural Network based on SURF (Speeded up Robust Feature) Detection. International Journal of Computer Applications. 175, 35 ( Dec 2020), 10-14. DOI=10.5120/ijca2020920903
This work presents the diagnosis of iris nevus (Cogan Reese) using a convolutional neural network (CNN) for its classification and Speeded Up robust feature (SURF) detection for its feature extraction. Iris nevus is a tumor found in the eye. Racial and environmental factors affect the color of the iris of a patient; hence, tumor may be seen in the eye background. In this work, the iris images will be tested and trained and will also describe the automatic diagnosis of iris nevus using neural network-based systems for its classification as nevus affected and unaffected iris. The model attained its best performance during training and testing with an accuracy of 97.50% and 80% respectively, a precision of 77% and a recall of 67%.