Classification of Eye Disorders based on Deep Convolutional Neural Network
Chandra Lekha Dondapati1, Ashutosh Ghosh2, TYJ. Naga Malleswari3
1Chandra Lekha Dondapati*, Department of Computer Science and Engineering, SRM Institute Of Science And Technology, Kattankulathur, India.
2Ashutosh Ghosh, Department of Computer Science and Engineering, SRM Institute Of Science And Technology, Kattankulathur, India.
3Dr. TYJ. Naga Malleswari, Department of Computer Science and Engineering, SRM Institute Of Science And Technology, Kattankulathur, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 28, 2020. | Manuscript published on April 10, 2020. | PP: 1388-1393 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4209049620/2020©BEIESP | DOI: 10.35940/ijitee.F4209.049620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Multiple Eye Diseases are currently diagnosed visually by ophthalmologists. In the beginning period, the huge scope screening of eye diseases is outlandish since there are less number of ophthalmologists and in addition these strategies expend additional time. This indicates that in order to correctly identify the disease, manual intervention and the proper infrastructure is important. Owing to the fact that many developing nations are not able to provide their masses with the basic healthcare facilities, the need for computer-aided systems that are robust and inexpensive increases manifold. Over the last few years, convolutional neural networks (CNN) are being increasingly employed for the task of automatic and semi-automatic image classification. Through this paper, we aim to develop a method using deep learning architecture to detect eye disorders in fundus images. In the initial step preprocessing is accomplished for the fundus image, trailed by feature extraction and order. Different evaluations of influenced pictures are tried by the proposed technique and the presentation has been looked at and examined. The models would be tested using standard evaluation metrics to evaluate the effectiveness of the models.
Keywords: Deep Learning, fundus image classification, convolutional neural networks, epoch.
Scope of the Article: Deep learning