BMC Bioinformatics

Table 5 Performance of experiments for dynamic model (RF) with F = 22 or 12 and CNN

From: Thermal face recognition under different conditions

	Dynamic model (RF)						CNN
	N = 5	N = 10	N = 15	N = 20	N = 25	N = 30	N = 5	N = 10	N = 15	N = 20	N = 25	N = 30
PUCV-DTF
Normal	99.48	100	100	100	100	100	99.13	100	100	100	100	100
Noise	95.87	96.74	97.74	97.83	98.61	99.74	98.26	99.13	99.48	99.74	99.87	99.91
Glasses (G)	98.57	100	100	100	100	100	99.78	100	100	100	100	100
Face mask(FM)	98.57	100	100	100	100	100	99.35	100	100	100	100	100
G + M	98.57	100	100	100	100	100	99.57	100	100	100	100	100
UCH-TTF
Normal	83.29	84.43	85.71	87.43	89.29	90.29	76.43	84.86	87.86	89.56	94.57	96.70
Noise	79.29	79.29	81.43	82.14	82.86	82.86	75.71	79.28	85.43	88.56	92.29	94.14
Glasses (G)	77.14	84.29	84.86	86.71	88.57	90.0	76.14	84.71	87.29	89.29	93.57	95.99
Face mask(FM)	77.14	84.29	84.86	86.71	88.57	90.0	75.86	83.86	86.99	89.29	93.14	95.70
G + M	77.14	84.29	84.86	86.71	88.57	90.0	74.77	82.14	86.29	88.70	91.14	92.43

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com