A Unified Factors Analysis Framework for Discriminative Feature Extraction and Object Recognition

Table 3

Best recognition rates of four algorithms on the testing sets of Yale.

LPP	63.5% ()	72.3% ()	80.5% ()
MFA	61.0% (13, 2, 2)	74.5% (14, 2, 1)	79.7% (21, 4, 2)
DLA	66.8% (15, 2, 2)	78.9% (23, 2, 1)	81.2% (13, 4, 2)
FA-LPP	73.2% (14, 2)	79.5% (16, 2)	85.4% (15, 4)

For LPP, the numbers in the parentheses are the selected subspace dimensions. For FA-LPP, the first numbers in the parentheses are the selected subspace dimensions and the second numbers are the parameters. For MFA and DLA, the first numbers in the parentheses are the selected subspace dimensions and the second and the third numbers are the parameters and , respectively.