• Sukhdeep Kaur
• Tanya Garg

The human eye is an essential part of the human body. Retina is a light-delicate layer at the back of the eye that spreads around 65 percent of its inside surface. Infected eyes have vascular insufficiencies, which means the system of vessels which supplies blood to the retina is immature. Segmentation of retinal layers from OCT images is fundamental to diagnose the progress of retinal diseases. This research work proposed a technique to segment the retina images based on neural network approach. The proposed technique utilizes gray-level co-occurrence matrix technique for feature extraction and artificial neural network for classification. MATLAB tool is used for implementation of the proposed technique. Results of the proposed technique are compared with the existing techniques such as ANN with filter approach, ANN with filter/SFS approach, and ANN with SFS approach. Classification accuracy and ROC curve are parameters that are used for evaluation of the results of proposed technique.

Segmentation, OCT images , gray-level co-occurrence matrix , ANN, SFS approach, ROC curve.

"A MODEL FOR AUTOMATIC DETECTION OF RETINA DISEASES.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.183-188, May 2019, Available :http://www.jetir.org/papers/JETIRCW06037.pdf

"A MODEL FOR AUTOMATIC DETECTION OF RETINA DISEASES.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp183-188, May 2019, Available at : http://www.jetir.org/papers/JETIRCW06037.pdf