Face%20Recognition%20Committee%20Machine

1
Face Recognition Committee Machine

• Term Three Presentation
• by
• Tang Ho Man

2
Outline

• Introduction
• Algorithms Review
• Face Recognition Committee Machine (FCRM)
• Distributed Face Recognition System (DFRS)
• Experimental Results
• Conclusion and Future Work
• Q A

3
Introduction

• Applications in security
• Authentication
• Identification
• Authentication measures
• Password
• Card/key
• Biometric

4
Introduction

• Face Recognition
• Training phase
• Recognition phase
• Objectives
• Comparison of different algorithms
• Face Recognition Committee Machine
• Distributed Face Recognition System

5
Review

• Algorithms in Committee Machine
• Eigenface
• Fisherface
• Elastic Graph Matching (EGM)
• Support Vector Machine (SVM)

6
Review Eigenface

• Application of Principal Component Analysis (PCA)
• Find eigenvectors and eigenvalues of covariance
  matrix C from training images Ti
• Training Recognition
• Project the images on face space
• Compare Euclidean distance and choose the closest
  projection

7
Review Fisherface

• Similar to Eigenface
• Application of Fishers Linear Discriminant (FLD)
• Minimize inner-class variations and maintain
  between-class discriminability
• Projection finding
• Between class scatter
• Within class scatter
• Projection

8
Review EGM

• Based on dynamic link architecture
• Extract facial feature by Gabor wavelet transform
  as a jet
• Face is represented by a graph G consists of N
  nodes of jets
• Compare graphs by cost function
• Edge similarity
• Vertex similarity
• Cost function

9
Review SVM

• Look for a separating hyperplane H which
  separates the data with the largest margin
• Decision function
• Kernel function
• Polynomial kernel
• Radial basis kernel
• Hyperbolic tangent kernel

10
FRCM - Overview

• Mixture of five experts
• Eigenface
• Fisherface
• EGM
• SVM
• Neural network

11
FRCM - Overview

• Elements in voting machine
• Result r(i)
• Individual experts result for test image
• Confidence c(i)
• How confident the expert on the result
• Weight w(i)
• Average performance of an expert

12
FRCM - Result Confidence

• Eigenface, Fisherface, EGM
• Use K nearest-neighbour classifiers
• Five nearest training set images are chosen
• Count number of votes for each recognized class
• Result
• Confidence

13
FRCM - Result Confidence

• SVM
• One-against-one approach with maximum voting used
• For J different classes, J(J-1)/2 SVM are
  constructed
• Confidence
• Neural network
• Binary vector of size J for target representation
• Result
• Class with output value closest to 1
• Confidence
• Output value

14
FRCM - Voting Machine

• Ensemble results, confidences from experts to
  arrive a final result
• Score function
• Final result Highest score class
• Advantages
• High performance
• High confidence

15
DFRS

• Motivation
• Real face recognition application
• Face recognition on mobile device
• Consists of
• Face Detection
• Face Recognition

16
DFRS - Limitations

• Memory
• Little memory for mobile devices
• Requirement for recognition
• Processing power

17
DFRS - Overview

• Client-Server approach
• Client
• Capture
• Ensemble
• Server
• Recognition

18
DFRS - Testing

• Implementation
• Desktop (1400MHz)
• Notebook (300MHz)

19
Experimental Results - Database

• ORL Face Database
• 40 people
• 10 images/person
• Yale Face Database
• 15 people
• 11 images/person

20
Experimental Results - ORL

• ORL Face database

21
Experimental Results - Yale

• Yale Face Database

22
Conclusion and Future Work

• Conclusion
• Comparison of different algorithms
• Committee machine improves accuracy
• Feasible on mobile device
• Future Work
• Use of dynamic structure
• Include more expert in the committee machine
• Implementation on PDA/Mobile

23
Question Answer Section

• Thanks!