DOIONLINE 
DOIONLINE Publish In |
International Journal of Electrical, Electronics and Data Communication (IJEEDC)-IJEEDC |
 Journal Home Volume Issue |
||||||||
Issue |
Volume-2,Issue-2 ( Feb, 2014 ) | |||||||||
Paper Title |
Computer Aided Automatic Glaucoma Diagnosis | |||||||||
Author Name |
Priya Kumbhare, Manisha Turkar, Rashmi Kularkar | |||||||||
Affilition |
Department of Electronics and Telecommunication Engineering, Rajiv Gandhi College of Engineering and Research, Nagpur, India | |||||||||
Pages |
28-32 | |||||||||
Abstract |
Abstract— This paper proposes the novel method for detection of glaucoma which is second leading cause of blindness worldwide Glaucoma is a group of diseases of the optic nerve involving loss of retinal ganglion cells. This is caused by increased pressure of fluid in the eye. This can result in decreased peripheral vision and, eventually, blindness. Untreated Glaucoma leads to permanent damage of the optic nerve and resultant visual field loss, which can progress to blindness. In this paper we use a combination of texture and higher order spectrum (HOS) features for detection of glaucoma from digital fundus images. The texture features include the co-ocurrence matrix and run length matrix based features. Minimum distance classifier and naïve bayes classifier are used to perform supervised classification \. The navie bayes classifier is found to be more accurate than the minimum distance classifier. Also the detection of glaucoma using HOS features is found to be more accurate than the textures features. Our proposed novel features are clinically significant and can be used to detect glaucoma accurately. Our project will be useful in easy and low cost detection of glaucoma so that it can be treated easily. Our goal is to develop an auto diagnostic system that will support the medical examination for finding glaucoma. | |||||||||
| View Paper | ||||||||||
