Skip to main content

Table 3 Performance (%) comparisons of different methods on FERET in size of 8 × 6 pixels

From: Class-specific kernel linear regression classification for face recognition under low-resolution and illumination variation conditions

Methods

PCA+Euclidean

PCA+Mahalanobis

KPCA-p

KPCA-g

LDA+Euclidean

Recognition rate

70.0

36.2

71.2

71.4

72.0

Methods

LDA+Mahalanobis

KLDA-p

KLDA-g

LRC

RLRC

Recognition rate

58.3

72.4

72.4

74.0

74.2

Methods

SRC

LPP

NPE

IPCR

URC

Recognition rate

73.8

61.2

28.0

63.5

71.6

Methods

LDRC

LBP

KLRC-p

KLRC-g

 

Recognition rate

76.0

53.8

76.8

76.4

 
  1. Italicized data means the proposed methods' results