Table 7.

Comparison of the proposed method with previous methods using CASIA v4.0 interval and IITD databases based on the RPF-measure evaluation protocol. A smaller value of σ and a higher value of µ show better performance. (unit: %) (The resultant values of GST [85], Osiris [86], WAHET [87], IFFP [88], CAHT [89], Masek [90], IDO [25], and IrisSeg [84] are referred from [84]).

DB	Method	R		P		F
		$\mathit{\mu }$	$\mathit{\sigma }$	$\mathit{\mu }$	$\mathit{\sigma }$	$\mathit{\mu }$	$\mathit{\sigma }$
CASIA V4.0 Interval	GST [85]	85.19	18	89.91	7.37	86.16	11.53
	Osiris [86]	97.32	7.93	93.03	4.95	89.85	5.47
	WAHET [87]	94.72	9.01	85.44	9.67	89.13	8.39
	IFFP [88]	91.74	14.74	83.5	14.26	86.86	13.27
	CAHT [89]	97.68	4.56	82.89	9.95	89.27	6.67
	Masek [90]	88.46	11.52	89	6.31	88.3	7.99
	IDO [25]	71.34	22.86	61.62	18.71	65.61	19.96
	IrisSeg [84]	94.26	4.18	92.15	3.34	93.1	2.65
	SegNet-Basic [57]	99.60	0.66	91.86	2.65	95.55	1.40
	Proposed Method	97.10	2.12	98.10	1.07	97.58	0.99
IITD	GST [85]	90.06	16.65	85.86	10.46	86.6	11.87
	Osiris [86]	94.06	6.43	91.01	7.61	92.23	5.8
	WAHET [87]	97.43	8.12	79.42	12.41	87.02	9.72
	IFFP [88]	93.92	10.62	79.76	11.42	85.83	9.54
	CAHT [89]	96.8	11.2	78.87	13.25	86.28	11.39
	Masek [90]	82.23	18.74	90.45	11 .85	85.3	15.39
	IDO [25]	51.91	15.32	52.23	14.85	51.17	13.26
	IrisSeg [84]	95.33	4.58	93.70	5.33	94.37	3.88
	SegNet-Basic [57]	99.68	0.51	92.53	2.05	95.96	1.04
	Proposed Method	98.0	1.56	97.16	1.40	97.56	0.84