Enhancing retinal vessel segmentation by color fusion

Xiaohong Wang, Xudong Jiang

Abstract: Accurate segmentation of retinal vessel plays an important role in the computer-aided diagnosis of eye diseases. Existing supervised methods extract features only from green channel due to its much higher contrast between vessel and background than in red and blue channels. However, red and blue channels also contain useful information for distinguishing vessel from background. This work investigates various ways of combining information in all 3 color channels to enhance the segmentation performance, based on which an effective color fusion scheme is proposed in this paper. Its performance is evaluated on two publicly available databases DRIVE and STARE. Results demonstrate that the proposed feature fusion with dimensionality reduction by asymmetric PCA visibly enhances the segmentation performance consistently on both databases, rendering better performance than state-of-the-art methods in dealing with healthy and pathological retinal images.