This research addresses the challenge of early detection and recognition of retinopathy, a common complication of diabetes that can lead to vision loss. We propose a novel approach utilizing hybrid methods for diabetic retinopathy recognition and detection. The proposed approach consists of four levels: pre-processing for noise removal and standardization of the input dataset, image segmentation using Spiking Neural Network (SNN) based on edge detection, dimension reduction and feature selection using percolation theory, and the final step of combining SNN and percolation theory for retinopathy area detection. Experimental results demonstrate that our proposed method outperforms existing approaches in terms of accuracy. By employing this approach, we aim to contribute to the early detection and prevention of retinopathy, thus mitigating the potential consequences of this disease and preserving eyesight.
Rahoo, L. A. (2023). Retinopathy Diabetic Recognition and Detection using novel Intelligent algorithms. Advances in Engineering and Intelligence Systems, 002(02), 107-113. doi: 10.22034/aeis.2023.397367.1100
MLA
Liaquat Ali Rahoo. "Retinopathy Diabetic Recognition and Detection using novel Intelligent algorithms". Advances in Engineering and Intelligence Systems, 002, 02, 2023, 107-113. doi: 10.22034/aeis.2023.397367.1100
HARVARD
Rahoo, L. A. (2023). 'Retinopathy Diabetic Recognition and Detection using novel Intelligent algorithms', Advances in Engineering and Intelligence Systems, 002(02), pp. 107-113. doi: 10.22034/aeis.2023.397367.1100
VANCOUVER
Rahoo, L. A. Retinopathy Diabetic Recognition and Detection using novel Intelligent algorithms. Advances in Engineering and Intelligence Systems, 2023; 002(02): 107-113. doi: 10.22034/aeis.2023.397367.1100
)