Authors: Tapesh Santra
patients get preventive care. Yet, due to lack of infrastructure and resources millions of patients do not avail such diagnosis. In this paper, I explore the possibility of developing an automatic retinal disease classifier using computer vision algorithms. Two different classes of algorithms are tested; (a) traditional computer vision approach of hand crafting features followed by developing machine learning (ML) models (b) automatic feature engineering and classification using more modern convolutional neural networks (CNN). The above algorithms were used to build both multi-class classifiers, i.e. the models which are trained to identify the correct disease, and binary classifiers, i.e. models that are trained to determine if a patient has a specific disease or not. A set of 600 pre-labelled retinal scan images were used to train the models. Both the ML and CNN models had relatively modest success in the multiclass scenario. However, the ML models were found to be reliably accurate in binary classification scenario, achieving >90% accuracy in identifying cataract.
Comments: 8 Pages. None
[v1] 2019-10-23 11:11:32
Unique-IP document downloads: 14 times
Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.
Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.