An Improved Multispectral Palmprint Recognition System Using Autoencoder with Regularized Extreme Learning Machine

Table 2

Comparison of recognition rates for the proposed approach with the state-of-the-art approaches for different spectral bands: blue, green, red, and NIR according to experimental model I.

Method [Ref.]	Recognition Rate (%)
	Blue	Green	Red	NIR
TPTSR [12]	78.13	98.02	98.58	98.34
NFS [13]	97.30	96.37	97.97	98.17
DWT [15]	93.83	93.50	95.20	94.60
FABEMD + TELM [19]	96.73	96.93	97.80	97.67
LBP-HF + Gabor [20]	98.02	98.37	98.74	98.67
Log-Gabor + [24]	99.23	99.10	99.30	99.33
Log-Gabor + [24]	99.03	98.90	99.13	98.93
Proposed Approach	100	100	100	99.83