| Popis: |
Glaucoma is one of the most common causes of blindness in the world. The vision lost due to glaucoma cannot be regained. Early detection of glaucoma is thus very important. The Optic Disk(OD), Optic Cup(OC) and Neuroretinal Rim(NRR) are among the important features of a retinal image that can be used in the detection of glaucoma. In this paper, a computer-assisted method for the detection of glaucoma based on the ISNT rule is presented. The OD and OC are segmented using watershed transformation. The NRR area in the ISNT quadrants is obtained from the segmented OD and OC. The method is applied on the publicly available databases HRF, Messidor, DRIONS-DB, RIM-ONE and a local hospital database consisting of both normal and glaucomatous images. The proposed method is simple, computationally efficient and achieves a sensitivity of 91.82% and an overall accuracy of 94.14%. |
