Leprosy Lesion Recognition Using Convolutional Neural Networks
Conference Paper, Proceedings of International Conference on Machine Learning and Cybernetics (ICMLC '16), pp. 141 - 145, July, 2016
Abstract
Leprosy, also known as Hansen’s disease, is a debilitating and chronic bacterial infection. As per World Health Organization’s report, there were 189,000 chronic cases of Leprosy in 2012 with 230,000 new diagnoses. Although curable at later stages, an early diagnosis prevents nerve involvement and the disabilities it incurs. The authors henceforth propose a Convolutional Neural Network based architecture for Leprosy lesion recognition. To train the network, authors use DermnetNz datasets along with web scraped images to achieve a best accuracy of 91.6% on a dataset split into 60% of training images, 20% of images are used for cross validation and 20% for testing.
BibTeX
@conference{Baweja-2016-102857,author = {Harjatin Singh Baweja and Tanvir Parhar},
title = {Leprosy Lesion Recognition Using Convolutional Neural Networks},
booktitle = {Proceedings of International Conference on Machine Learning and Cybernetics (ICMLC '16)},
year = {2016},
month = {July},
pages = {141 - 145},
keywords = {Convolutional Neural Networks; Computer Vision; Leprosy; Hansen’s disease; Artificial Neural Networks; Tensor Flow},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.