Accurate leukocoria predictor based on deep VGG‐net CNN technique. Issue 10 (8th July 2020)

• Record Type: Journal Article
• Authors: Subrahmanyeswara Rao, Boyina
• Is Part Of: IET image processing. Volume 14:Issue 10(2020)
• Page Start: 2241
• Page End: 2248
• Publication Date: 2020-07-08
• Subjects: feature extraction -- image classification -- computer vision -- learning (artificial intelligence) -- medical image processing -- eye -- patient treatment -- convolutional neural nets; convolutional neural networks -- general image recognition -- object detection -- face recognition -- leukocoria detection -- infant retinal treatment -- abnormal white reflection -- deep Visual Geometry Group‐net CNN classifier -- automatic detection -- feature extraction -- convolution layer -- eye images -- accurate leukocoria predictor -- deep VGG‐net CNN technique -- digital image analysis -- object classification -- deep learning -- computer vision problems -- pooling layer -- fully connected layer; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6656
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : The most important part of digital image analysis is object classification. Nowadays, deep learning makes an enormous achievement in computer vision problems. So there has been a lot of interests in applying features learned by convolutional neural networks (CNNs) on general image recognition to more tasks such as object detection, segmentation and face recognition. Leukocoria detection is one of the serious challenges in infant retinal treatment. Leukocoria is represented as an abnormal white reflection appearing in the eyes of an infant suffering from retinoblastoma. This research proposes a deep Visual Geometry Group‐net CNN classifier for automatic detection of leukocoria. The proposed classifier comprises pre‐processing, feature extraction and classification. The deep CNN classifier contains convolution layer, pooling layer and fully connected layer with weights are developed on each image. Experimental results based on several eye images consist of ordinary and leukocoric from flicker, and it demonstrates that the proposed classifier provides better results with the accuracy of 98.5% and the error rate is below 2% which exceeds the current results.