Glaucoma is an ocular disorder produced due to its raised fluid pressure in the optic nerve. It harms the optic nerve consequently resulting in sight loss. Automatic analysis of retina images is becoming an important screening tool now days. This technique helps to detect various kind of risks and diseases of eyes. This paper focuses on the feature extraction from images as well as classification for enhancing the performance of the overall system. It is extremely hard to identify glaucoma disease portion without segmenting the image. Consequently in this research, fuzzy based segmentation algorithm is deployed as primary phase of the work. Then, features are extracted from the segmented image. After that, by utilizing filtering approaches, feature selection is carried out. Finally, classification approach is carried out with the help of the deep learning algorithm. Therefore, in this research, a novel method for an automated diagnosis of glaucoma is introduced utilizing digital fundus images dependent upon fuzzy segmentation, which is utilized to segment the image into numerous parts. Improved wavelet transform is employed for feature extraction. Depending upon filter based feature selection algorithm, these extracted features are ranked and features are utilized for the classification of normal and glaucoma images with the help of Deep Neural Network (DNN) classifier. The simulation environment is carried out in MATLAB and it is clear that the proposed research technique improved precise diagnosis of glaucoma from the fundus images.

Glaucoma is a retinal disease that damages the eye's optic nerve, frequently causing an irreversible loss of vision. However, the accurate diagnosis of this disease is difficult but early-stage diagnosis may cure this retinal disease. The objective of this research is to diagnose glaucoma disease in the top of the eye's optical nerve. The proposed approach detects glaucoma via four major steps namely Data enhancement phase, segmentation phase, feature extraction phase, and classification phase by the fractional gravitational search-based hybrid deep neural network (FGSA-HDNN) classifier. The proposed classifier is used for the exact classification of glaucoma infected images and normal images. Here, the proposed approach utilizes the statistical, textural, and vessel features from the segmented output. Also, the proposed FGSO algorithm is used for testing the deep neural network. From the experimental results, it is observed that the proposed glaucoma detection has obtained a sensitivity of 99.64%, a specificity of 97.84%, and an accuracy of 98.75% that outperforms other state-of-art methods.