A hybrid method for accurate iris segmentation on at-a-distance visible-wavelength images

EURASIP Journal on Image and Video Processing

Table 7 Performance comparison with 5 degrees of rotation for each test carried out to assess the robustness

Blur	Noise	Dice	Precision	Recall	Error	Exec. time
0	–	0.9158	0.8993	0.9373	0.0109	1.0430
0	Gaussian	0.8900	0.8561	0.9319	0.0148	0.8703
0	Poisson	0.9140	0.8946	0.9380	0.0114	0.8628
0	Salt & pepper	0.8729	0.8427	0.9216	0.0159	0.8611
3	–	0.8968	0.9147	0.8860	0.0128	0.9992
3	Gaussian	0.8822	0.8617	0.9095	0.0158	0.8508
3	Poisson	0.8968	0.9076	0.8920	0.0131	0.8700
3	Salt & pepper	0.8386	0.8280	0.8708	0.0189	0.8488
6	–	0.7877	0.8429	0.7570	0.0244	0.8686
6	Gaussian	0.8034	0.8075	0.8121	0.0253	0.7729
6	Poisson	0.8118	0.8547	0.7885	0.0219	0.8030
6	Salt & pepper	0.7490	0.7687	0.7693	0.0275	0.7686