face recognition & biometric systems, 2005/2006 face recognition process

26
Face Recognition & Biometric Systems, 2 005/2006 Face recognition process

Upload: vincent-banks

Post on 18-Dec-2015

227 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face recognition process

Page 2: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Plan of the lecture

Face recognition processMost useful tools Principal Components Analysis Support Vector Machines Gabor Wavelets Hough Transform

Biometric methods

Page 3: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face recognition process

Detection Normalisation

Featureextraction

Feature vectorscomparison

Page 4: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face detection: aims

Find a face in the image independent of image size independent of face size for RGB and GS images fast & effective independent from head rotation angle

Face location passed to normalisation

Page 5: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face detection: toolsGeneralised Hough Transform ellipse detection

Support Vector Machines (SVM) verification

PCA (back projection) verification

Gabor Wavelets feature points detection

Colour-based face maps

Page 6: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face detection: algorithm

Detection of ”vertical” ellipses face candidates

Detection of ”horizontal” ellipses eye sockets candidates

Initial normalisation and verificationDetection of feature points

Page 7: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face tracking

Useful in case of video sequences faster than detection smaller precision

Tool: Optical flowTracking of feature points

Page 8: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Normalisation

Input: image from a camera characteristic points location

Target: generate an image of invariant

parameters eliminate differences within classes

Page 9: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Normalisation: tools

Geometrical transformsImage filteringHistogram modifications histogram fitting to a histogram

of the average face image

Lighting compensation

Page 10: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Normalisation: stages

Rotation of non-frontal facesGeometrical normalisationLighting compensationHistogram fitting

Page 11: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Feature extraction

Input: normalised image

Target: generate a key which describes the

face algorithm of comparing the keys

Page 12: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Feature extraction: tools

Principal Component Analysis Linear Discriminant Analysis Local PCA Bayesian Matching

Gabor Wavelets

Page 13: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Feature vectors comparison

Coherent with feature extractionEigenfaces geometric distances SVM

Dual Eigenfaces image difference classified

Elastic Bunch Graph Matching correlation based

Page 14: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Multi-method fusion

Many feature extraction methods

S1

S2

Sn

... S

K1

K2

Kn

...

Two images Feature vectors Similarities

K1

K2

Kn

...

Page 15: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Multi-method fusion

Average similarity weighted mean

SVM with polynomial kernelSVM for finding optimal weights

Page 16: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Tools: PCA

Applications: feature extraction – the Eigenfaces

method detection (back projection) Dual Eigenfaces

Stages: training feature extraction feature vectors comparison

Page 17: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Tools: SVM

Applications: face detection – verification feature vectors comparison detection of lighting direction estimation of head rotation angle multi-method fusion image quality assessment

Page 18: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Tools: SVM

Stages: training classification

Main idea: data mapped into higher dimension to

achieve linear separability mapping performed by application of

kernels

Problems with training setParameters must be selected properly

Page 19: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Tools: Gabor Wavelets

Applications: feature extraction (EBGM method) feature points detection face tracking (the detected points are

tracked)

Properties: local frequency analysis set of various wavelets prepared comparison: correlation with displacement

estimation

Page 20: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Tools: GHT

Useful for face detectionProperties: directional image generated (set of

segments) probable ellipse centre for every

segment (based on templates) accumulation of the results for all

the segments in the image

Page 21: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Biometric methods

Types of the methods: static dynamic (behavioural)

Requirements: universality distinctiveness permanence collectability performance acceptability circumvention

Page 22: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Face recognitionAdvantages: low invasiveness high speed identification support system

Drawbacks: relatively low effectiveness changeability of a face face is not always visible

Page 23: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Fingerprint recognition

Advantages: high effectiveness useful for forensic applications

Disadvantages: long acquisition time low acceptability

Page 24: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Iris recognition

Advantages: high distinctiveness universality

Drawbacks: high quality image required low permanence in young age

Page 25: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Behavioural methods

Gait recognitionVoice recognitionSignature analysis

Page 26: Face Recognition & Biometric Systems, 2005/2006 Face recognition process

Face Recognition & Biometric Systems, 2005/2006

Thank you for your attention!