Diabetic retinopathy (DR) is a serious eye condition that can lead to blindness. Owing to the advancement of technology, computer-aided diagnosis enables clinicians to act swiftly in the diagnosis of DR. The study explores the efficacy of feature-based transfer learning in the classification of DR by examining the ability of two pre-trained convolutional neural networks architecture, i.e.,MobileNet and MobileNetV2 in extracting meaningful features from retina scanned images. The Logistic Regression (LR) is used to classify the different classes of DR from the extracted features. It was shown from the present study that the MobileNet+LR yielded a better classification of the classes. It further demonstrates its feasibility as a plausible tool for early detection and treatment of the disease.
Improving Diabetic Retinopathy Classification: A MobileNet Feature-Based Transfer Learning with Logistic Regression Investigation
Lect. Notes in Networks, Syst.
International Conference on Robot Intelligence Technology and Applications ; 2023 ; Taicang December 06, 2023 - December 08, 2023
2024-11-29
7 pages
Article/Chapter (Book)
Electronic Resource
English
INTRODUCTION TO DIABETIC RETINOPATHY AND EARLY DIABETIC RETINOPATHY
British Library Conference Proceedings | 2006
|Forecasting Fire Using MobileNet Architecture
IEEE | 2023
|