A method for blood vessel segmentation in retinal images using morphological reconstruction

The retinal blood vessels is an important indicator for diagnosis of several clinical disorders of eye. In this paper an automated method for blood vessel extraction has been presented. In the first stage, the extracted green channel image is enhanced using contrast limited adaptive histogram equalization (CLAHE) and 2D Gabor wavelet. Then the enhanced image is segmented using morphological reconstruction and hysteresis thresholding. A final segmented image is obtained by the application of a two stage post-processing phase. The performance of the proposed method is evaluated and tested on the CHASE_DB1 by reaching an average accuracy of 0.950.