International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 46 - Number 1 |
Year of Publication: 2012 |
Authors: Amineh Naseri, Ali Pouyan, Nader Kavian |
10.5120/6873-8977 |
Amineh Naseri, Ali Pouyan, Nader Kavian . Automatic Detection of Retina Layers using Texture Analysis. International Journal of Computer Applications. 46, 1 ( May 2012), 29-33. DOI=10.5120/6873-8977
In this paper, two computer approaches is proposed for recognition of retina layers on optical coherence tomography (OCT) images. OCT uses the optical backscattering of light to scan the eye and describe a pixel representation of the anatomic layers within the retina. Our approaches is based on co-occurrence matrix for feature extraction and a neural network and a supervised learning method for classification, which four features of this matrix have been selected as a feature vector by support vector machine (SVM) and multilayer perceptron (MLP) have been used for classifying retina layers. Achieved results of combined these methods in the best state was 96. 6% precision by MLP and 98. 6% by SVM method. These results show that apply these methods on OCT images discriminate retina layers with efficient accuracy. Since, recognition of retina layers is important for automatic analyzing of OCT images, therefore our proposed methods can be very useful.