Journal of Electrical and Computer Engineering / 2016 / Article / Tab 1

Research Article

Multialgorithmic Frameworks for Human Face Recognition

Table 1

Recognition accuracies of uncorrelated face recognition methods and their fusion using different normalization and fusion techniques.

AlgorithmsDatabaseNormalization techniquesAccuracies (%)
UnibiometricMultialgorithmic fusion
Sum ruleMax ruleMin rule

Eigenfaces (E)
Fisherfaces (F)
LBP (L)
A-LBP (A)
AT & T (ORL) [17] MM(E): 95.45(E + L): 95.32(E + L): 95.38(E + L): 94.97
(F): 97.50(F + L): 97.79(F + L): 97.50(F + L): 97.28
(L): 94.52(E + A): 97.05(E + A): 95.42(E + A): 96.86
(A): 95.00(F + A): 97.95(F + A): 97.50(F + A): 97.50

Eigenfaces (E)
Fisherfaces (F)
LBP (L)
A-LBP (A)
AT & T (ORL) [17] Tanh(E): 96.54(E + L): 95.64(E + L): 93.24(E + L): 95.38
(F): 97.50(F + L): 97.79(F + L): 97.50(F + L): 97.44
(L): 94.49(E + A): 97.31(E + A): 94.97(E + A): 95.13
(A): 94.87(F + A): 97.95(F + A): 97.44(F + A): 97.60

Eigenfaces (E)
Fisherfaces (F)
LBP (L)
A-LBP (A)
LFW [18]MM(E): 65.00(E + L): 72.24(E + L): 72.18(E + L): 60.32
(F): 70.00(F + L): 72.50(F + L): 72.14(F + L): 70.00
(L): 65.29(E + A): 72.50(E + A): 72.46(E + A): 62.11
(A): 67.37(F + A): 72.14(F + A): 70.25(F + A): 69.29

Eigenfaces (E)
Fisherfaces (F)
LBP (L)
A-LBP (A)
LFW [18]Tanh(E): 65.03(E + L): 69.93(E + L): 71.73(E + L): 65.19
(F): 69.84(F + L): 72.50(F + L): 70.19(F + L): 67.91
(L): 65.42(E + A): 72.62(E + A): 69.93(E + A): 65.03
(A): 67.12(F + A): 72.24(F + A): 72.30(F + A): 67.91

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.