SEGMENTATION OF OPTIC DISC IN FUNDUS IMAGES

Glaucoma is one of the leading eye diseases that cause blindness. Early detection of glaucoma is essential to minimize the risk of visual loss of diabetic patients. A standard procedure that is used for the detection of glaucoma and other eye diseases is done by manual examination of the optic disc by an ophthalmologist. The proposed work implements automatic optic disc segmentation of fundus images of the eye. Automatic retinal image analysis is emerging as an important screening tool for early detection of eye diseases. This method better captures the boundary of a non-homogeneous object such as the optic disc (OD). Depending on the shape of this boundary, one can find whether the person is affected by glaucoma or not. Active contour models like Gradient Vector Flow model and Chan-Vese model fail to localize disc boundaries due to gradient and global information (gray level intensities, contour lengths, region areas). The proposed region-based active contour model utilizes local image information around each point of interest in multi-dimensional feature space to provide robustness against variations found in and around the OD region. This model defines a local energy functional to achieve desired OD segmentation. This energy is minimized to OD boundary using level set method.