A Synthetic Fusion Rule Based on FLDA and PCA for Iris Recognition Using 1D Log-Gabor Filter

Table 1

Result with different downsampling factors and different patches.

		Original; (%)			Imadjust; (%)			Clahe; (%)			msr; (%)
		bilinear	bicubic	PCA/; FLDA	bilinear	bicubic	PCA/; FLDA	bilinear	bicubic	PCA/; FLDA	bilinear	bicubic	PCA/; FLDA
	PSNR	38.40	39.52	41.73	37.68	38.67	40.06	34.24	36.73	38.24	38.97	40.20	41.94
1/2	MSE	10.27	7.31	4.39	11.18	8.90	6.45	24.67	13.90	9.81	8.30	6.25	4.19
	SSIM	0.67	0.8	0.9	0.8	0.77	0.86	0.66	0.66	0.79	0.79	0.84	0.91
	PSNR	40.68	40.94	41.12	40.11	39.43	40.21	38.19	37.27	38.78	41.31	41.60	41.66
1/4	MSE	5.60	5.27	5.06	6.39	7.46	6.24	9.93	12.28	8.66	4.85	4.53	4.47
	SSIM	0.85	0.86	0.88	0.85	0.82	0.86	0.78	0.73	0.82	0.89	0.9	0.89
	PSNR	40.96	41.01	41.99	39.93	40.12	41.01	38.77	38.30	39.08	41.57	41.41	42.01
1/6	MSE	5.25	5.19	4.14	6.65	6.37	5.19	8.68	9.68	8.09	4.56	4.73	4.12
	SSIM	0.88	0.88	0.9	0.85	0.85	0.88	0.81	0.79	0.83	0.9	0.89	0.9
	PSNR	41.58	41.70	42.29	40.79	40.36	40.93	38.94	38.38	39.27	41.48	41.41	42.16
1/8	MSE	4.55	4.43	3.86	5.46	6.02	5.29	8.35	9.50	7.75	4.66	4.73	3.98
	SSIM	0.89	0.89	0.91	0.87	0.86	0.88	0.83	0.8	0.83	0.89	0.89	0.91