Blood Vessel Segmentation of Fundus Retinal Images Based on Improved Frangi and Mathematical Morphology

Table 2

Performance comparison of blood vessel segmentation methods with the DRIVE data set.

Methods	Evaluation indicators
	Acc	Se	Sp
Chaudhuri et al. [6]	0.8773	0.3357	0.9794
Li et al. [7]	0.9343	0.7154	0.9716
Barkana et al. [32]	0.9502	0.7224	0.9840
Hassanien et al. [33]	0.9388	0.7210	0.9710
Rezaee et al. [18]	0.9463	0.7189	0.9793
Zhao et al. [17]	0.9477	0.7354	0.9789
Fu et al. [34]	0.9470	0.7294	—
Guo et al. [35]	0.9613	0.9859	0.7046
Budak et al. [36]	0.9685	0.7439	0.9900
Guo et al. [37]	0.9075	0.8990	0.9283
The proposed method	0.9554	0.6942	0.9802