biometric recognition in spatial frequency domain · recognition --- correlation filters face...
TRANSCRIPT
1
Vijayakumar Bhagavatula
Vijayakumar Bhagavatula
Biometric Recognition in Spatial Frequency Domain
2
Vijayakumar Bhagavatula
Acknowledgments
Dr. Marios SavvidesDr. Chunyan XieDr. Jason ThorntonDr. Krithika VenkataramaniPablo HenningsJingu HeoSungwon ParkRamzi AbiantonRamamurthy Bhagavatula
Technology Support Working Group (TSWG)CyLab
3
Vijayakumar Bhagavatula
Outline
Use of spatial frequency domain for image recognition --- Correlation filtersFace recognitionIris recognitionFingerprint recognitionFace tracking examplesSummary
5
Vijayakumar Bhagavatula
Challenge: Pattern VariabilityChallenge: To tolerate pattern variability (some times called distortions) while maintaining discriminationFacial appearance changes due to illuminationFingerprint image changes due to plastic deformation
6
Vijayakumar Bhagavatula
Pattern Recognition ApproachesFeatureComputation
Feature Extraction
Classification
PriorKnowledge
Transform-ations
Statistics/Training Data
INPUT
CLASS
Statistical pattern recognition (e.g., Minimum error rate methods)Nonparametric methods (e.g., Nearest-neighbor methods)Discriminant methods (e.g., linear discriminant functions, artificial neural networks, support vector machines, etc.)Correlation filters
7
Vijayakumar Bhagavatula
Correlation Pattern Recognition
Determine the cross-correlation between the reference and test images for all possible shifts.
When the target image matches the reference image exactly, output is the autocorrelation of the reference image; autocorrelation peaks at origin.
If the input r(x) contains a shifted version s(x-x0) of the reference signal, the correlator will exhibit a peak at x=x0.
If the input does not contain the reference signal s(x), the correlator output will be low .
If the input contains multiple replicas of the reference signal, resulting cross-correlation contains multiple peaks at locations corresponding to input positions.
( ) ( ) ( )c r x s x dxτ τ= −∫
Ref: B.V.K. Vijaya Kumar, A. Mahalanobis and R. Juday, Correlation Pattern Recognition, Cambridge University Press, UK, November 2005.
8
Vijayakumar Bhagavatula
Shift-InvarianceDesired pattern can be anywhere in the input scene.Multiple patterns can appear in the scene.Simple matched filters unacceptably sensitive to rotations, scale changes, etc.
9
Vijayakumar Bhagavatula
Correlation Plane Contour Map Correlation Plane Contour Map
Correlation Plane SurfaceCorrelation Plane Surface
M1A1 in the open M1A1 near tree line
SAIP ATR SDF Correlation Performance for Extended Operating
Conditions
Courtesy: Northrop Grumman
Adjacent trees cause some correlation noise
10
Vijayakumar Bhagavatula
Correlation Filters
MatchNo Match
DecisionTest Image IFFT Analyze
Correlation output
FFT
Correlation Filter
Filter Design . . .Training Images
TrainingRecognition
11
Vijayakumar Bhagavatula
Peak to Sidelobe Ratio (PSR)
σmeanPeakPSR −
=
1. Locate peak1. Locate peak
2. Mask a small 2. Mask a small pixel regionpixel region
3. Compute the mean and 3. Compute the mean and in a in a bigger region centered at the peakbigger region centered at the peak
PSR invariant to constant illumination changes
Match declared when PSR is large, i.e., peak must not only be large, but sidelobes must be small.
12
Vijayakumar Bhagavatula
CMU PIE Database
13 cameras21 Flashes
Ref: T. Sim, S. Baker, and M. Bsat, “The CMU pose, illumination, and expression (PIE) database,” Proc. of the 5th IEEE Intl. Conf. on Automatic Face and Gesture Recognition, May 2002.
13
Vijayakumar Bhagavatula
PIE Database, one face under 21 illuminations65 subjects
14
Vijayakumar Bhagavatula
Train on 3, 7, 16, Train on 3, 7, 16, --> Test on 10.> Test on 10.
Match Quality = 40.95
15
Vijayakumar Bhagavatula
Using the same filter as before, Match Quality = 30.60
Occlusion of Eyes
16
Vijayakumar Bhagavatula
Match Quality = 22.38
Uncentered Images
17
Vijayakumar Bhagavatula
ImpostorUsing someone else’s filterPSR = 4.77
18
Vijayakumar Bhagavatula
Filter h
The center of correlation output
An image in the frequency domain in vector form xi
N images
Distortion-tolerant Correlation Filter Design
xd×d Xd×d
… …
xi
FFT
2 1 2[ , ,..., ]Nd N×=X x x x
……
hd2×1 d2×1 Hd×d
(0,0)i i ic + += =h x x h
19
Vijayakumar Bhagavatula
Minimum Average Correlation Energy Filter
Minimizing average correlation energy can be done directly in the frequency domain by averaging the correlation plane energies Ei as follows.
hDhhXXh iii
d
kid
d
pidi kXkHpcE ++
==
==== ∑∑ *
1
221
1
21 )()()(
⎥⎥⎥⎥⎥⎥
⎦
⎤
⎢⎢⎢⎢⎢⎢
⎣
⎡
)(.
)3()2(
)1(
dX
XX
X
i
i
i
i
DhhhXXh +
=
+
=
=⎥⎥⎦
⎤
⎢⎢⎣
⎡== ∑∑
N
iiiN
N
iiNave EE
1
*1
1
1
h = D-1 X (X+ D-1 X)-1 c
Minimizing average correlation energy h+Dh subject to the constraints X+h=c leads to the MACE filter solution
Ref: A. Mahalanobis, B.V.K. Vijaya Kumar, and D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, pp. 3633-3630, 1987.
20
Vijayakumar Bhagavatula
2D Impulse Response of MACE Filter
22
Vijayakumar Bhagavatula
Features of Correlation Filters
Shift-invariant; no need for centering the test imageGraceful degradationCan handle multiple appearances of the reference image in the test imageClosed-form solutions based on well-defined metrics
Ref: B.V.K. Vijaya Kumar, A. Mahalanobis and Richard D. Juday, Correlation Pattern Recognition,Cambridge University Press, UK, November 2005.
23
Vijayakumar Bhagavatula
PCA in Frequency DomainIs there any advantage to carrying out PCA on the Fourier transforms of training images?Since FT is a unitary transformation, apparently no differences (except for sign changes) in the eigenfaces obtained via space domain or frequency domain.
24
Vijayakumar Bhagavatula
Phase retains more image information
27
Vijayakumar Bhagavatula
EigenphasesPCA carried out on the phase-only versions of training image Fourier transforms
Frequency DomainFrequency Domain
Space DomainSpace Domain
28
Vijayakumar Bhagavatula
Experiments
5-10,18,19,208
18,19,20153,16,207
8,9,10143,10,166
6,7,8131,2,7,165
7,10,19124,7,134
5,7,9,10112,7,163
5-10101,10,162
5-1293,7,161
29
Vijayakumar Bhagavatula
Test Images
Training Images used were full imagesTraining Images used were full images
30
Vijayakumar Bhagavatula
Recognition Rates (Full Test Images)
Ref: M. Savvides, and B.V.K. Vijaya Kumar, “Eigenphases Vs. Eigenfaces,” Intl. Conf. on Pattern Recognition (ICPR), Cambridge, England, 2004.
31
Vijayakumar Bhagavatula
Recognition of Left-half Blocked Test Images
32
Vijayakumar Bhagavatula
Recognition of Test Images with Eye Region
33
Vijayakumar Bhagavatula
Face Recognition Grand Challenge (FRGC)
Ver 2.0625 Subjects; 50,000 Recordings; 70 Gbytes
To facilitate the advancement of face recognition research, FRGChas been organized by NIST
* P. J. Phillips, P. J. Flynn, T. Scruggs, K. W. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min, and W. Worek, "Overview of the Face Recognition Grand Challenge," In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2005
34
Vijayakumar Bhagavatula
FRGC Dataset: Experiment 4
Generic Training Set consisting of 222 people with a total of 12,776 images
Gallery Set of 466 people (16,028) images total
Feature extraction Feature space generation
Reduced Dimensionality Feature Representation of Gallery Set
16,028
Probe Set of 466 people (8,014) images total
Reduced Dimensionality Feature Representation of Probe Set
8,014
Similarity Matching
Reduced Dimensional Feature Space
project project
35
Vijayakumar Bhagavatula
FRGC “Gallery” Images
Controlled (Indoor) Controlled (Indoor)
16,028 gallery images of 466 people
36
Vijayakumar Bhagavatula
FRGC “Probe” Images
Uncontrolled (Indoor)
37
Vijayakumar Bhagavatula
FRGC “Probe” Images
Uncontrolled (Outdoor)
Outdoor illumination images are very
challenging due to harsh cast shadows
38
Vijayakumar Bhagavatula
FRGC Baseline Results
The verification rate of PCA is about 12% at False Accept Rate 0.1%.
ROC curve from P. Jonathan Phillips et al (CVPR 2005)
39
Vijayakumar Bhagavatula
Correlation Filters for Face Verification
Enrollment
Similarity Score
Verification
Only 1
Low performance
256 million correlations
Long time
40
Vijayakumar Bhagavatula
Class-dependence Feature Analysis (CFA)
MotivationImprove the recognition rate by using the generic training setReduce the processing time by extracting features using inner products
Class-dependence Feature AnalysisModel a population for recognition using a set of people.
41
Vijayakumar Bhagavatula
CFA
Extract features using correlation filtersRedundant class-dependence feature analysis (CFA)
– Train a correlation filter for each subject from the generic training set
– Extract a feature vector for each image by inner product
– Calculate the similarity score
42
Vijayakumar Bhagavatula
Class Dependent Feature Analysis (CFA)
2y
ymace-2
T hy
Class1
….
-mace-2h
Class2 Class 222
…
1y 3y
uX)DX(XDh 111mace
−−+−=
⎥⎥⎥⎥
⎦
⎤
⎢⎢⎢⎢
⎣
⎡
=
n
2
1
u
uu
u
T0] 0 0 0[u1 =T1111][u2 = T0] 0 0 0[u222 =
In this figure, we’re building the MACE filter for class 2
43
Vijayakumar Bhagavatula
CFA - 2
CFA basis vectors
-1maceh 2-maceh 3-maceh 222-maceh
…
]...[x]h...hh[xy 22221k222-mace2-mace1-macekk cccH TT ===kx
TN21 uuuu ],...,,[=
T]N11 1 .. 1 1 [1u =hmace-1 : all zeros except u1
……… T]N222222 1 .. 1 1 [1u =hmace-222 : all zeros except u222
Test input with no trained filters
uX)DX(XDh 111mace
−−+−=
]...[),(...),(,([ 22221 cccKKK == k222-macek2-macek-1macek xhxh ),xhy
Linear CFA
Nonlinear CFA using Kernels
44
Vijayakumar Bhagavatula
KCFA Timeline
0
0 . 2
0 . 4
0 . 6
0 . 8
1
Ex p 4
Verif
icat
ion
Rat
es
P CAGS LDA
CFAKCFA- v 1KCFA- v 3
KCFA- v 5
82.4% @ 0.1 % FAR
(Latest Performance)
57
Vijayakumar Bhagavatula
Iris Pattern
Detail from biological tissue:
Muscle ligaments
Connective tissue of stromal layer
Anterior folds, furrows, crypts
Random, detailed arrangement of tissue
58
Vijayakumar Bhagavatula
Iris Segmentation
Eye image Bounded iris region
“Unwrapped” iris pattern
Standard iris segmentation: commonly used, proposed by Daugman
1 J.G. Daugman, “High Confidence Visual Recognition of Persons by a Test of Statistical Independence,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1148-61, Nov. 1993.
1
59
Vijayakumar Bhagavatula
Iris Pattern “Unwrapping”
60
Vijayakumar Bhagavatula
Iris Recognition: Correlation FiltersWe use correlation filters for iris recognition. We design a filter for each iris class using a set of training images.
match
no match
FFT-1x
Correlation filter
FFT
Determining an iris match with a correlation filter
Segmented iris pattern
64
Vijayakumar Bhagavatula
Iris Pattern Deformation
Video Example
Landmark points for all images within one class
Clear deformation from:
Tissue changes AND/OR
Deviations in iris boundaries.
65
Vijayakumar Bhagavatula
Eyelid Occlusion
Example : Eyelid artifacts in segmented pattern.
upper eyelid
lower eyelid
lower eyelid
Example: match comparison
For significant portion of area, similarity is lost.
66
Vijayakumar Bhagavatula
ApproachProblem summary
Accurate pattern matching when patterns experience
relative nonlinear deformations
and partial occlusions
in addition to blurring and observation noise.
PATTERN SAMPLE
PATTERN TEMPLATE
GENERATE EVIDENCE
ESTIMATE STATES
MATCH SCORE
ApproachPROBABILISTIC MODEL:
DEFORM & OCCLUSION STATES
67
Vijayakumar Bhagavatula
Probabilistic Method
Model :
Set of observed variables O (similarity cues, eyelid cues).
Set of hidden variables H (relative transformation states).
Given : Pair of iris patterns to compare.
Estimate : Conditional distribution
Prior probability
Rewards reasonable transformations
Observation Likelihood
Likelihood of observed data, given transformation
68
Vijayakumar Bhagavatula
Hidden Variables : Deformation
Iris plane partitioned into 2D field:
Deformation described by vector field:
69
Vijayakumar Bhagavatula
Hidden Variables : Occlusion
Occlusion described by binary field:
Hidden vars:
Field resolution tradeoff
> representative power
> computation
70
Vijayakumar Bhagavatula
Deformation Evidence
Evidence about local similarities between template and image:
Correlation filter output
Produces similarity cues across local alignments.
Robust to pattern corruption by noise.
71
Vijayakumar Bhagavatula
Eyelid Evidence
Classifier : Fisher Linear Discriminant in statistical feature space
-1 -0.8 -0.6 -0.4 -0.2 0 0.2 0.4 0.6 0.80
1
2
3
4x 10-3
Marginal separation, but enough for useful cues.
non-occluded
occluded
Example classifier output
This yields local occlusion cues .
72
Vijayakumar Bhagavatula
Probabilistic Model Dependencies
Local observed variables: Local hidden variables:
73
Vijayakumar Bhagavatula
Goal : Infer posterior distribution on hidden states:
Matching Process
Template
New pattern
Similarity evidence
Eyelid evidence
Inference technique :Loopy belief propagation
74
Vijayakumar Bhagavatula
After Inference : Match Score Computation
Deterministic match score
Average similarity across unoccluded iris regions:
Better : Probabilistic match score
Expected score with respect to estimated posterior:
Advantage : accounts for uncertainty in the posterior.
75
Vijayakumar Bhagavatula
Example : Match Comparisons
Template
Authentic
Match score:
0.28
Impostor
Match score:
0.01
77
Vijayakumar Bhagavatula
78
Vijayakumar Bhagavatula
ICE Phase I : Performance
Verification Rate at FAR = 0.1%
Experiment 1: 99.63 % Experiment 2: 99.04 %
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.80
0.02
0.04
0.06
0.08
0.1
0.12
0.14
non-match scores
match scores
Experiment 1 score distribution
84
Vijayakumar Bhagavatula
86
Vijayakumar Bhagavatula
NIST 24 DatabaseDigital Video of Live-scan Fingerprint Data Optical sensor DFR-90 from Identicator technology of 500 dpi resolutionChosen data set - plastic distortion set
The finger is rolled and twisted10 fingers of 10 people ( 5 female and 5 male )10 secs of MPEG2 movie per finger
300 images of size 448x478 pixels (padded to 512x512 pixels)Chosen subset - 10 thumb prints
Class 3 Class 10
87
Vijayakumar Bhagavatula
Evaluation ProtocolTraining - uniformly sampled images from the 300 images of a classTest - correlate filters of each class against 300 images of all classes
Images of the same class as the filter – 300 authentics per filterImages of a different class from the filter – 2700 impostors per filte
88
Vijayakumar Bhagavatula
Resolution Effect
128x128 64x64256x256512x512 32x32
K. Venkataramani, B.V.K. Vijaya Kumar, “Fingerprint verification using correlation filters”, Audio-and Video- based Biometric Person Authentication (AVBPA), UK, 2003 .
0.6%
89
Vijayakumar Bhagavatula
Palmprints
Palmprints have a conglomerate of features.These include principal lines, smaller creases or wrinkles, fingerprint-like ridges and textures.Palmprints can be easily aligned about fiducial points of the hand’s geometry or shape.
90
Vijayakumar Bhagavatula
Palmprint Verification
Design ProcessDesign Process
Training ImagesTraining Images
CorrelationCorrelationFilterFilter
FFTFFT IFFTIFFT VerificationVerification
AuthenticAuthentic ImposterImposter
91
Vijayakumar Bhagavatula
Experiment SpecificationsPolyU Palmprint Database100 palms (classes)Left hands flipped to look as right hands3 images per class for training3 images per class for testing5 different experiments using region sizes with sides of 64, 80, 96, 112, and 128 pixels
Left handLeft hand Left hand flippedLeft hand flipped Right handRight handDatasetDataset
usedused
92
Vijayakumar Bhagavatula
Palmprint Verification Results
104
Vijayakumar Bhagavatula
SummaryCorrelation filters
Achieved excellent performance in face recognition grand challenge (FRGC)Performed very well in iris challenge evaluation (ICE)Also successful in fingerprint recognition and palmprintrecognition
Correlation filters provide a single matching engine for a variety of image biometrics --- making multi-biometric approaches feasible.