Earlier glaucoma detection using blood vessel segmentation and classification

Glaucoma is the retinal disorder which is leading cause for blindness. Glaucoma is classified into two types namely open angle glaucoma and closed angle glaucoma. Earlier detection of glaucoma will prevent the vision loss. This work is aimed to detect the glaucoma in the retinal image and classify them based on their severity. To detect the abnormality, preprocessing methods such as filtering, green channel extraction and CLAHE are proposed and for feature extraction namely optic disc ratio, active contour and blood vessel segmentation are proposed. Extracted Features are given as the input for classification based on ANFIS and SVM. Then sensitivity, specificity and accuracy of two classifiers are compared to attest an efficient diagnosis system for screening the Glaucoma disorder.