An Image Based Classification Method for Cataract

Currently, surgery is the most effective and common way to treat cataract, one of the leading causes for blindness worldwide. Of all surgical methods, phacoemulsifieation is the most popular. During the operation, surgeons have to evaluate the hardness degree of the cataractous lens by themselves. To make the evaluation intelligent, a machine-aided classification method for cataractous lens is proposed in this paper. Based on the microscope images of cataractous lens, color information of cataractous lens with different hardness degrees is investigated. K-nearest neighbor classifiers are used to classify different hardness degrees of cataractous lens. The proposed method has been tested using real microscope images of phacoemulsifieation. Recognition rate of 92.5% has been achieved.