|
Block Based Probability Intensity Feature Extraction for Automatic Glaucoma Detection
|
|
| Author:
|
M. ARULMARY, DR. S.P. VICTOR
|
| Abstract:
|
Automatic glaucoma detection is one of the interesting areas for more researchers. There are several researches based
on Cup to Disc Ratio. The objective of this paper is to identify glaucoma suspect eyes with high accuracy. In this paper,
features are extracted by dividing the fundus images into blocks and identifying the high intensity value in each block.
The glaucoma suspect images have larger number of blocks with high intensity whereas the normal eyes have lesser. The
features are trained and classified using Support Vector Machine (SVM) classifier. The proposed method is tested in
RIM-One r3 database. The experimental results substantially showed that the proposed method achieves 92% specificity
at 86% sensitivity with 0.865 AUC.
|
| Keyword:
|
SVM classifier, Cup to Disc Ratio, Intra Ocular Pressure, ELM classifier
|
| EOI:
|
-
|
| DOI:
|
-
|
| Download:
|
Request For Article
|
|
|