Face Recognition Committee Machine

23
Face Recognition Committee Machine Term Three Presentation by Tang Ho Man

description

Face Recognition Committee Machine. Term Three Presentation by Tang Ho Man. Outline. Introduction Algorithms Review Face Recognition Committee Machine (FCRM) Distributed Face Recognition System (DFRS) Experimental Results Conclusion and Future Work Q & A. Introduction. - PowerPoint PPT Presentation

Transcript of Face Recognition Committee Machine

Page 1: Face Recognition  Committee Machine

Face Recognition Committee Machine

Term Three Presentation

by

Tang Ho Man

Page 2: Face Recognition  Committee Machine

Outline

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

Page 3: Face Recognition  Committee Machine

Introduction

Applications in security Authentication Identification

Authentication measures Password Card/key Biometric

Page 4: Face Recognition  Committee Machine

Introduction

Face Recognition Training phase Recognition phase

Objectives Comparison of different algorithms Face Recognition Committee Machine Distributed Face Recognition System

Page 5: Face Recognition  Committee Machine

Review

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

Page 6: Face Recognition  Committee Machine

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

Page 7: Face Recognition  Committee Machine

Review – Fisherface

Similar to Eigenface Application of Fisher’s Linear Discriminant (FLD) Minimize inner-class variations and maintain between-

class discriminability

Projection finding Between class scatter Within class scatter Projection

Page 8: Face Recognition  Committee Machine

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

Page 9: Face Recognition  Committee Machine

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

Page 10: Face Recognition  Committee Machine

FRCM - Overview

Mixture of five experts Eigenface Fisherface EGM SVM Neural network

Page 11: Face Recognition  Committee Machine

FRCM - Overview

Elements in voting machine Result r(i)

Individual expert’s result for test image Confidence c(i)

How confident the expert on the result Weight w(i)

Average performance of an expert

Page 12: Face Recognition  Committee Machine

FRCM - Result & Confidence

Eigenface, Fisherface, EGM Use K nearest-neighbour classifiers

Five nearest training set images are chosenCount number of votes for each recognized class

Result Confidence

Page 13: Face Recognition  Committee Machine

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

Page 14: Face Recognition  Committee Machine

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

Page 15: Face Recognition  Committee Machine

DFRS

Motivation Real face recognition application Face recognition on mobile device

Consists of Face Detection Face Recognition

Page 16: Face Recognition  Committee Machine

DFRS - Limitations

Memory Little memory for mobile devices Requirement for recognition

Processing power

Page 17: Face Recognition  Committee Machine

DFRS - Overview

Client-Server approach Client

CaptureEnsemble

ServerRecognition

Page 18: Face Recognition  Committee Machine

DFRS - Testing

Implementation Desktop (1400MHz) Notebook (300MHz)

Page 19: Face Recognition  Committee Machine

Experimental Results - Database

ORL Face Database 40 people 10 images/person

Yale Face Database 15 people 11 images/person

Page 20: Face Recognition  Committee Machine

Experimental Results - ORL

ORL Face database

Page 21: Face Recognition  Committee Machine

Experimental Results - Yale

Yale Face Database

Page 22: Face Recognition  Committee Machine

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

Page 23: Face Recognition  Committee Machine

Question & Answer Section

Thanks!