Curvelet Transform Based on Edge Preserving Filter for Retinal Blood Vessel Segmentation

Segmentation of vessel in retinal fundus images is a primary step for the clinical identification specific eye diseases. Effective diagnosis vascular pathologies from angiographic thus vital aspect and generally depends on segmentation structure. Although various approaches are extensively utilized, however, responses lower at vessel's edges. The curvelet transform signifies edges better than wavelets, hence convenient multiscale edge enhancement. bilateral filter nonlinear that capable providing effective smoothing while preserving strong Fast an advanced version regulates contrast Therefore, this paper fusion algorithm recommended by fusing fast can effectively preserve details has capability to detect direction feature investigation tracking significant characteristics image. Afterwards C mean thresholding used extraction vessel. approach assessed DRIVE dataset. Experimental results illustrate preserved advantages both provides result. demonstrate method outperforms traditional approaches.