A morphologic two-stage approach for automated optic disk detection in color eye fundus images

A new adaptive morphological method for the automatic detection of the optic disk in digital color eye fundus images is presented in this paper. This method has been designed to detect the optic disk center and the optic disk rim. In our experiments with the DRIVE and DIARETDB1 databases, the proposed method was able to detect the optic disk center with 100% and 97.75% of accuracy, respectively. We considered correct all automatically detected optic disk location that is within the borders of the optic disk marked manually. Using our proposed method, the rim of the optic disk was detected in all images of the DRIVE database with average sensitivity and specificity of 83.54% and 99.81%, respectively, and on the DIARETDB1 database with average sensitivity and specificity of 92.51% and 99.76%, respectively.

► We show how the optic disk can be detected in color eye fundus images.
► We propose to use a new mathematical morphology approach to detect the optic disk rim and location.
► We obtain low false positives/negatives rates, desirable features in optic disk detection.
► Our experiments suggest that highly accurate results are achievable.