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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improving Diabetic Retinopathy Classification: A MobileNet Feature-Based Transfer Learning with Logistic Regression Investigation


    Additional title:

    Lect. Notes in Networks, Syst.


    Contributors:

    Conference:

    International Conference on Robot Intelligence Technology and Applications ; 2023 ; Taicang December 06, 2023 - December 08, 2023



    Publication date :

    2024-11-29


    Size :

    7 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    INTRODUCTION TO DIABETIC RETINOPATHY AND EARLY DIABETIC RETINOPATHY

    Bailey, C. / Great Britain | British Library Conference Proceedings | 2006


    Detection and Classification of Diabetic Retinopathy using Raspberry PI

    Vidhya Lavanya, R / EP, Sumesh / Jayakumari, C et al. | IEEE | 2020


    Expectation maximization based logistic regression for breast cancer classification

    Rajaguru, Harikumar / Prabhakar, Sunil Kumar | IEEE | 2017


    Forecasting Fire Using MobileNet Architecture

    Sungeetha, D. / PushpaLatha, S. / Legapriyadharshini, N. et al. | IEEE | 2023