• Dev Dhirendra Bafna
• Dipak Gaikar
• Yash Desale
• Chinmay Jadhav
• Anurag Yadav

This Diabetic retinopathy is a disease caused by uncontrolled chronic diabetes that can lead to complete blindness if not treated in a timely manner. Therefore, early medical diagnosis of diabetic retinopathy and its medical treatment are essential to prevent serious side effects of diabetic retinopathy. Manual detection of diabetic retinopathy by ophthalmologists takes a lot of time and currently causes great suffering to patients. Automated systems help detect diabetic retinopathy quickly and make it easy to follow up on treatment to avoid further effects on the eyes. In this paper, we extracted three features such as effusion, hemorrhage, and microaneurysm and then after extracting these 3 features we classified them using a hybrid classifier that combines them with support vector machine, k-nearest neighbor, random forest, logistic regression, and multilayer perceptron network for machine learning method to classify. Hence, the proper analysis of retinal vessel is required to get the precise result, which can be done by Retinal Segmentation. Using the image classifier we can classify the infected eye from the normal eye just by uploading the image which saves time and money of the user, allowing him to check the symptoms at home rather than going to hospital. So we developed a system to reduce time.

Diabetic retinopathy, automated system, machine learning, deep learning, dataset, processing, CNN, DenseNet

"Vision Guard using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p500-p506, April-2024, Available :http://www.jetir.org/papers/JETIR2404G65.pdf

"Vision Guard using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp500-p506, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G65.pdf