OBJECTIVE: The primary objective of this article is to present a summary of different types of image processing methods employed for the detection of glaucoma, a serious eye disease. INTRODUCTION: Glaucoma affects the optic nerve in which retinal ganglion cells become dead, and this leads to loss of vision. The principal cause is the increase in intraocular pressure, which occurs in open-angle and angle-closure glaucoma, the two major types affecting the optic nerve. In the early stages of glaucoma, no perceptible symptoms appear. As the disease progresses, vision starts to become hazy, leading to blindness. Therefore, early detection of glaucoma is needed for prevention. METHODOLOGY/APPROACH: Manual analysis of ophthalmic images is fairly time-consuming and accuracy depends on the expertise of the professionals. Automatic analysis of retinal images is an important tool. Automation aids in the detection, diagnosis, and prevention of risks associated with the disease. Fundus images obtained from a fundus camera have been used for the analysis. Requisite pre-processing techniques have been applied to the image and, depending upon the technique, various classifiers have been used to detect glaucoma. CONCLUSION: The techniques mentioned in the present review have certain advantages and disadvantages. Based on this study, one can determine which technique provides an optimum result.
OBJECTIVE: The primary objective of this article is to present a summary of different types of image processing methods employed for the detection of glaucoma, a serious eye disease. INTRODUCTION:Glaucoma affects the optic nerve in which retinal ganglion cells become dead, and this leads to loss of vision. The principal cause is the increase in intraocular pressure, which occurs in open-angle and angle-closure glaucoma, the two major types affecting the optic nerve. In the early stages of glaucoma, no perceptible symptoms appear. As the disease progresses, vision starts to become hazy, leading to blindness. Therefore, early detection of glaucoma is needed for prevention. METHODOLOGY/APPROACH: Manual analysis of ophthalmic images is fairly time-consuming and accuracy depends on the expertise of the professionals. Automatic analysis of retinal images is an important tool. Automation aids in the detection, diagnosis, and prevention of risks associated with the disease. Fundus images obtained from a fundus camera have been used for the analysis. Requisite pre-processing techniques have been applied to the image and, depending upon the technique, various classifiers have been used to detect glaucoma. CONCLUSION: The techniques mentioned in the present review have certain advantages and disadvantages. Based on this study, one can determine which technique provides an optimum result.
Entities:
Keywords:
Bayes and SVM classifier; CDR and ISNT ratio; K-means clustering; PCA; glaucoma