Face Recognition Technique: A Literature Survey on Face Recognition and Insight on Machine Recognition Using by Manisha Urkude & S. Kishor & S. Naranje
Author:Manisha Urkude & S. Kishor & S. Naranje [Urkude, Manisha]
Language: eng
Format: epub
Publisher: MANISHA URKUDE
Published: 2015-08-01T22:00:00+00:00
Fig 3.3.1.2 ComparisonComparison of KSM and RBM algorithm
KSM Algorithm Eigenface Algorithm 86% 66.90%
Table 3.3.1.6 Recognition rate of KSM and Eigenface algorithm
90% 86%
80% 70% 66.90%
60%
50%
40%
30%
20%
10%
0% KSM Algorithm Eigenface Algorithm
Fig 3.3.1.3 ComparisonComparison of KSM and Eigenface algorithm
KSM Algorithm LDA Algorithm 86% 56.10%
Table 3.3.1.7 Recognition rate of KSM and LDA algorithm
90%86%
80%
70% 60% 56.10%
50%
40%
30%
20%
10%
0% KSM Algorithm LDA Algorithm
Fig 3.3.1.4 ComparisonComparison of KSM and LDA algorithm
KSM Algorithm Pixel Algorithm 86% 51.30%
Table 3.3.1.8 Recognition rate of KSM and Pixel algorithm
90% 86%
80%
70%
60% 51.30%
50%
40%
30%
20%
10%
0% KSM Algorithm Pixel Algorithm
Fig 3.3.1.5 ComparisComparison of KSM and Pixel algorithm
Occlusion by sunglasses Sample A (KSM) Sample B(RoBM) Ka=43 Kb=770
Na=50 Nb=912
Pa=0.86 Pb=0.8443 Pa-Pb=0.0157
Z=0.299
Probability
One tail Two tail 0.3825 0.7649
Table 3.3.1.9 Z ratio of KSM and RoBM algorithm Sample A (KSM) Sample B(RBM) Ka=43 Kb=563
Na=50 Nb=912
Pa=0.86 Pb=0.6173 Pa-Pb=0.2427
Z=3.46
Probability
One tail Two tail 0.0003 0.0005
Table 3.3.1.10 Z ratio of KSM and RBM algorithm Sample A (KSM) Sample B(Eigenface) Ka=43 Kb=610
Na=50 Nb=912
Pa=0.86 Pb=0.6689 Pa-Pb=0.1911
Z=2.818
Probability
One tail Two tail 0.0024 0.0048
Table 3.3.1.11 Z ratio of KSM and Eigenface algorithm Sample A (KSM) Sample B( LDA ) Ka=43 Kb=515
Na=50 Nb=912
Pa=0.86 Pb=0.5647 Pa-Pb=0.2953
Z=4.119
Probability
One tail Two tail <.0001 <.0002
Table 3.3.1.12 Z ratio of KSM and LDA algorithm Sample A (KSM) Sample B(Pixel) Ka=43 Kb=469 Na=50 Na=912
Pa=0.86 Pb=0.5143 Pa-Pb=0.3457
Z=4.771
Probability
One tail Two tail <.0001 <.0002
Table 3.3.1.13 Z ratio of KSM and Pixel algorithm (http://vassarstats.net/propdiff_ind.html)
Download
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.
Deep Learning with Python by François Chollet(12647)
Hello! Python by Anthony Briggs(9948)
OCA Java SE 8 Programmer I Certification Guide by Mala Gupta(9825)
The Mikado Method by Ola Ellnestam Daniel Brolund(9814)
A Developer's Guide to Building Resilient Cloud Applications with Azure by Hamida Rebai Trabelsi(9726)
Dependency Injection in .NET by Mark Seemann(9370)
Hit Refresh by Satya Nadella(8857)
Algorithms of the Intelligent Web by Haralambos Marmanis;Dmitry Babenko(8335)
The Kubernetes Operator Framework Book by Michael Dame(7948)
Sass and Compass in Action by Wynn Netherland Nathan Weizenbaum Chris Eppstein Brandon Mathis(7811)
Test-Driven iOS Development with Swift 4 by Dominik Hauser(7791)
Exploring Deepfakes by Bryan Lyon and Matt Tora(7737)
Grails in Action by Glen Smith Peter Ledbrook(7722)
Practical Computer Architecture with Python and ARM by Alan Clements(7683)
Implementing Enterprise Observability for Success by Manisha Agrawal and Karun Krishnannair(7647)
Robo-Advisor with Python by Aki Ranin(7635)
The Well-Grounded Java Developer by Benjamin J. Evans Martijn Verburg(7592)
Building Low Latency Applications with C++ by Sourav Ghosh(7524)
Svelte with Test-Driven Development by Daniel Irvine(7504)
