• G. Swaraj
• Dr. Y. Praveen Kumar
• k.naveen
• p. lakshmi Kamal
• Shubham Jauke

The human eye plays a crucial role in vision, and early detection of eye diseases is essential to prevent permanent vision loss. Traditional diagnostic methods rely heavily on manual examination by ophthalmologists, which can be time-consuming and prone to human error. This paper presents a deep learning-based system for the classification and early detection of eye disorders such as diabetic retinopathy, glaucoma, and cataracts using retinal images. The proposed system employs Convolutional Neural Networks (CNNs) along with transfer learning techniques using EfficientNet to improve classification performance. Image preprocessing methods such as resizing, normalization, and data augmentation are applied to enhance model accuracy and robustness. The system performs multi-class classification and provides prediction confidence scores. Experimental results demonstrate that the model achieves high accuracy and reliability, making it suitable for real-time medical applications. The system aims to assist ophthalmologists, reduce diagnostic delays, and improve access to healthcare services, especially in resource-limited areas.

Deep Learning, Eye Diseases, CNN, Diabetic Retinopathy, Glaucoma, Image Classification

"Deep Learning-Based Classification and Early Detection of Eye Disorders", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.g674-g681, March-2026, Available :http://www.jetir.org/papers/JETIR2603686.pdf

"Deep Learning-Based Classification and Early Detection of Eye Disorders", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppg674-g681, March-2026, Available at : http://www.jetir.org/papers/JETIR2603686.pdf