Retinal Vessel Segmentation Using Local Entropy Thresholding

This paper presents an efficient method for automatic detection and extraction of blood vessels in retinal images. The proposed algorithm is composed of four steps: matched filtering, local entropy thresholding, length filtering, and morphological thinning. The purpose of matched filtering is to enhance the blood vessels. Entropy thresholding can well keep the spatial structure of vascular tree segments. Length filtering is used to remove misclassified pixels. The algorithm has been tested on twenty ocular fundus images.

[1]  Liang Zhou,et al.  The detection and quantification of retinopathy using digital angiograms , 1994, IEEE Trans. Medical Imaging.

[2]  A. Pinz,et al.  Mapping the human retina , 1996, IEEE Transactions on Medical Imaging.

[3]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[4]  Guoliang Fan,et al.  An efficient blood vessel detection algorithm for retinal images using local entropy thresholding , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[5]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.