Eye Disease Classification based on Deep Belief Networks
K. G. Rani Roopha Devi1, R. Mahendra Chozhan2

1K. G. Rani Roopha Devi, Ph.D Scholar, Madurai Kamaraj University, Madurai (Tamil Nadu), India.
2R. Mahendra Chozhan, Dental Clinic, Kodaikanal, Periyakulam, Lakshmipuram (Tamil Nadu), India.
Manuscript received on 18 October 2019 | Revised Manuscript received on 25 October 2019 | Manuscript Published on 02 November 2019 | PP: 3273-3278 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B15520982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1552.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Problems affecting the eye can range from infections of the eye or the eyelid, genetically inherited eye problems, eye injuries or objects in the eye, and eye disorders that are the result of conditions that affect many organs. While classification of disease stages is critical to understanding disease risk and progression, several systems based on red tissues eye photographs are known. Most of these require in-depth and time-consuming analysis of eye images. Herein, we present an automated computer-based classification algorithm using Deep belief networks (DBNs), as well as network initialization effect to classify isolated events. Classification is a data mining (machine learning) technique used to predict group membership for data instances. In Image classification analyzes the numerical properties of various image features and organizes data into categories. To simplify the problems of prediction or classification, neural networks are being introduced. In this paper, the introduction of Deep- belief network (DBN) to classify the types of diseases affects the human eye. The DBN classify the three types of diseases such as defected eye, conjunctivitis, Keratoconus, and other types of diseases. The eye diseases features are compared with the features of the database. Finally the classification output produces the types of diseases present in the eye image. The implementations are done using the Matlabsoftware. Finally, the classification performances of DBN architecture were analyzed using the accuracy, precision and recall parameters etc.
Keywords: Eye Diseases, Deep Belief Networks, Classifier, Image Classification, Feature Extraction.
Scope of the Article: Classification