• M.NEVEATHA

Glaucoma is a disease in which fluid pressure in the eye increases continuously, and damages the optic nerve and leads to vision loss. It is the second leading cause of blindness. For identification of disease in human eyes, the databases which can be obtained from the clinical decision support system based on the retinal image analysis technique. For accurate glaucoma detection, first, we preprocess the image using a median filter. After preprocessing the image is decomposed by using a wavelet transform. The features are extracted by using the Gray level co-occurrence matrix. The extracted features are classified as a normal or glaucomatous image using a Probabilistic neural network classifier, we classify that the given image is the normal or glaucomatous image. If the image is tested as glaucoma with their cup to disc ratio values it is classified as early, moderate, and severe stage. CDR value is less than 0.3 is considered as normal. If the CDR value greater than 0.3 -0.5 is considered as an early stage.If the CDR value greater than 0.6-0.7 is considered a moderate stage. If the CDR value greater than 0.8-0.9 is considered a severe stage.we observed glaucoma detection with an accuracy of 98.7%

Cup to disc ratio, glaucoma, PNN classifier, wavelet transform.

"CLASSIFICATION AND DETECTION OF GLAUCOMA FROM FUNDUS IMAGE USING WAVELET TRANSFORM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.489-496, June 2019, Available :http://www.jetir.org/papers/JETIR1906X97.pdf

"CLASSIFICATION AND DETECTION OF GLAUCOMA FROM FUNDUS IMAGE USING WAVELET TRANSFORM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp489-496, June 2019, Available at : http://www.jetir.org/papers/JETIR1906X97.pdf