Download presentation
Presentation is loading. Please wait.
Published byTiana Welding Modified over 9 years ago
1
Face Recognition and Biometric Systems Elastic Bunch Graph Matching
2
Face Recognition and Biometric Systems Plan of the lecture Eigenfaces – main drawbacks Alternative approaches EBGM method (Elastic Bunch Graph Matching) Gabor Wavelets face feature points detection feature vectors comparison
3
Face Recognition and Biometric Systems Recognition process DetectionNormalisation Ekstrakcja cech Feature vectors comparison Feature extraction
4
Face Recognition and Biometric Systems Eigenfaces Face represented by a vector loss of 2D information Holistic approach face is treated as a monolithic object No difference between intra- and extra-personal features
5
Face Recognition and Biometric Systems Feature extraction methods Based on PCA nature of features taken into account 2D information utilised face topology taken into account Based on feature points similarity wavelets methods shape comparison
6
Face Recognition and Biometric Systems EBGM - introduction Approximate location of feature points Frequency analysis of feature points a set of wavelets convolution between wavelet and image Feature vectors comparison based on exact feature points detection
7
Face Recognition and Biometric Systems EBGM - introduction
8
Face Recognition and Biometric Systems Wavelet transform Fourier transform frequency domain Gaussian distribution added Local frequency analysis wavelength ( ) wavelet orientation ( ) Gaussian radius ( ) Set of various wavelets
9
Face Recognition and Biometric Systems Wavelet transform Point (x 0, y 0 )
10
Face Recognition and Biometric Systems Wavelet transform Point (x 0, y 0 )
11
Face Recognition and Biometric Systems Wavelet transform Imaginary part can be eliminated Phase shift ( ) can be modified to get two values
12
Face Recognition and Biometric Systems Wavelet transform Varying wavelet orientation ( ) Varying wavelength ( )
13
Face Recognition and Biometric Systems Wavelet transform Varying phase ( ) Varying Gaussian radius ( )
14
Face Recognition and Biometric Systems Wavelet transform Convolution calculated in a point C is a complex number The result presented in phazor form
15
Face Recognition and Biometric Systems Wavelet transform Set of N wavelets various properties optimisation – wavelets calculated once Set of feature points Convolution between wavelets and the image in every feature point Feature vector of a feature point (J - jet): values of convolutions
16
Face Recognition and Biometric Systems Wavelet transform Modification of feature point location module (a j ) – value rather stable argument ( j ) – value can change significantly
17
Face Recognition and Biometric Systems Feature vectors comparison Correlation N – number of wavelets
18
Face Recognition and Biometric Systems Feature vectors comparison Covariance
19
Face Recognition and Biometric Systems Feature vectors comparison Correlation with displacement correction
20
Face Recognition and Biometric Systems Displacement correction Influence on phase shift works for displacements smaller than /2 Displacement estimation convolution calculated in every point results comparison displacement found by correlation maximisation
21
Face Recognition and Biometric Systems Displacement correction Approximation with Taylor expansion Analytical solution
22
Face Recognition and Biometric Systems Displacement correction This works for small displacements only maximal acceptable displacement depends on the wavelength it’s better to start with low frequencies
23
Face Recognition and Biometric Systems Features detection Set of perfect data (M images) real positions of feature points in M images average dependencies between positions A „bunch” created for every feature point bunch – set of M feature vectors
24
Face Recognition and Biometric Systems Features detection New image approximate feature points’ locations For every feature point: compare with every feature vector in a bunch (maximized correlation) choose the „expert” correct the position based on displacement from the „expert”
25
Face Recognition and Biometric Systems Features detection Set of detected feature points Estimated location of a new point Exact location (find the displacement) Add the point to the set
26
Face Recognition and Biometric Systems EBGM algorithm 1. Estimate location of features 2. For every point: 1. calculate convolutions with all wavelets (create a Jet) 2. find the displacement (it can be used for detection) 3. correct the Jet for the new location 3. Feature vectors comparison: 1. sum of correlations, feature points location 2. SVM-based comparison (correlations classified)
27
Face Recognition and Biometric Systems EBGM algorithm Image normalisation for EBGM frequency must not be affected Standard operations geometric normalisation histogram modifications Smoothed edges sharp edges influence the frequency
28
Face Recognition and Biometric Systems EBGM algorithm
29
Face Recognition and Biometric Systems Summary Slower method than Eigenfaces High effectiveness Feature-based approach possible fusion with the Eigenfaces Helpful for feature detection
30
Face Recognition and Biometric Systems Thank you for your attention! Plan: 20/05Filtering, lab @12am (2nd sect.) 27/05No lecture, lab @8am (2nd sect.) 03/06Summary, lab @10am + @ 1pm (1st & 3rd sect.)
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.