• PONAGANTI CHANDU
• Dr.I.Kullayamma

In this study, we are focus on Diabetic Retinopathy (DR) classification and symptom analysis using Convolutional Neural Networks (CNNs). The methodology begins with preprocessing steps including image resizing to ensure uniformity, conversion to grayscale, noise removal using Median Filtering. Histogram Equalization and contrast adjustment further enhance image quality for improved feature extraction. Segmentation is performed using k-means clustering to isolate regions of interest indicative of DR severity. Training options are carefully selected to maximize classification accuracy, evaluated using a confusion matrix. The classification outputs include Mild DR, Moderate DR, No DR, Proliferative DR, and Severe DR stages. Additionally, symptoms analysis aids in understanding disease progression and severity. The study aims to achieve high accuracy in DR diagnosis, facilitating early intervention and personalized treatment strategies.

Diabetic Retinopathy Dataset, Pre-Processing, Convolution Neural Network, Deep learning, Classification, Symptoms, Accuracy.

"Diabetic Retinopathy Classification and Symptom Analysis Using Convolutional Neural Networks ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.e464-e473, November-2024, Available :http://www.jetir.org/papers/JETIR2411454.pdf

"Diabetic Retinopathy Classification and Symptom Analysis Using Convolutional Neural Networks ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. ppe464-e473, November-2024, Available at : http://www.jetir.org/papers/JETIR2411454.pdf