SIFT Based Vein Recognition Models: Analysis and Improvement

Table 2

Influence of selected CEs on the number of detected SIFT keypoints (PUT Vein Database).

Capturing session		Linear/nonlinear functional enhancement (LNFE)
	Original	IN	GLS	CS	GC08	LS	UM	HBF	HF	INE
S1	6	19	71	16	11	13	70	19	6	7
S2	11	19	84	15	14	12	72	18	7	8
S3	15	13	43	11	14	18	88	17	11	12
Average	11	17 (1.5)	62 (5.6)	14 (1.3)	12 (1.1)	15 (1.4)	86 (7.8)	18 (1.6)	9 (0.8)	10 (0.9)
Image set	HE and its variants (HEs)					Hierarchical enhancement models (HEM)
	Original	HE	AHE	CLAHE	CLHE	IHE	DHE	RASF	HHE	HEHBF
S1	6	24	333	103	22	97	449	88	110	52
S2	11	30	350	29	31	116	385	82	135	52
S3	15	38	286	70	35	132	406	113	115	83
Average	11	33 (3.0)	322 (29.3)	59 (5.4)	31 (2.8)	127 (11.5)	426 (38.7)	89 (8.1)	127 (11.5)	69 (6.3)