Detection of Primary Glaucoma Using ANN with the Help of Back Propagation Algo in Bio-medical Image Processing

Abstract

One of the dreaded diseases that adversely affects human eye in the world is the Glaucoma. It should be remembered that without eyes, nothing is possible in this world. Further, as per the WHO, it is a well-known fact that the glaucoma is determined as the second largest disease across the globe. Proper care should be taken to avoid this at an early stage, as this would later result in the loss of human vision. The glaucoma disease occurs in the human eyes because of the increase in the intraocular pressure of the fluid flow in the drainage canal of human eyes. To reduce the glaucoma treatment expenses, we are devising a low cost module method for detecting the primary glaucoma in the humans using their fundus images. The images of the infected eye will be captured by the fundus camera, analyzed & a info is given to the patient that he/she is affected with the glaucoma disease. Once the person comes to know that they are affected, then proper diagnosis can be done by gathering consultations from the medical experts. The method of detecting the primary glaucoma is being presented in this section using a revised artificial neural network along with a back propagation algorithm concepts. The morphological operators concepts are being used for the processing the cup and the disc & finally the region of interest, i.e., the cup and the disc areas are detected from which the infected ratio is computed. Using a revised feature extraction process, the features of the captured disc & the cup can be efficiently detected with a concept of CDR detection and the result will declare whether the input test image is glucomatic or not. Simulations have been done in the Matlab environment. Databases have been taken from the hospitals & online. The simulation results have shown the effectivity of the method proposed in this extensive research work.