Vision—Feature Extraction Topics Part I •Fourier Transform
Transcript of Vision—Feature Extraction Topics Part I •Fourier Transform
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction
Topics
Part I•Fourier Transform •Windowed Fourier Transform•Wavelets
Part II•Principal Component Analysis•Independent Component Analysis
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction I
2 ( )ˆ ( , ) ( , ) x y
y
j x yxf f x y e dxdyπ ω ωω ω
∞ ∞− +
−∞ −∞
= ∫ ∫Fourier Transform
x
yImage(B)(A)
Spectrum
xω
yω
Amplitude of (A) &Phase of (B)
Phase carries Information
Courtesy of Professors Tomaso Poggio and Sayan Mukherjee. Used with permission.
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction I
Template Matching' ' '( ) ( ) ( ) ( ) ( )c x f x g x x dx h x g x
∞
−∞
= − = −∫' ' ' ˆ ˆˆ( ) ( ) ( ) ( ) ( ) ( )c x f x h x x dx c f hω ω ω
∞
−∞
= − =∫
Result c
Template g
Image f
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction I
Windowed Fourier Transform
2( , ) ( ) ( ) j uf t f u g u t e duπωω∞
−
−∞
= −∫%
2inst( ) cos( ),f t t tπ ω= = ( )g t ( , )f tω%
( )f uu
( )g u t−
t T− t
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction I
Wavelet Transform
,1( )s t p
u tus s
ψ ψ − = ,( , ) ( ) ( )s tT s t f u u duψ
∞
−∞
= ∫
2
0.5, 10
1,0
2,15
( ) red
green blue
uu ueψψ
ψ
ψ
−
− −
−
=
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction I
Haar Wavelets (Matlab Toolbox)
Screenshot from Matlab Toolbox removed due to copyright reasons.
Pattern Recognition for VisionFall 2004
Vision—Feature Extraction II
Principal and Independent Component Analysis
x1
PCA
ICA
PCA
ICA
x2PCA:•Decorrelated•OrthogonalICA:•Statistically Independent
Image removed due to copyright considerations. See Figure 1 in: Baek, Kyungim, et. al. "PCA vs. ICA: A comparison on the FERET data set."International Conference of Computer Vision, Pattern Recognition, and ImageProcessing, in conjunction with the 6th JCIS. Durham, NC, March 8-14 2002, June 2001.
Pattern Recognition for VisionFall 2004
Pattern Recognition—Classifiers
Topics
Fisher Discriminant Analysis (FDA)•Support Vector Machines (SVM)
Pattern Recognition for VisionFall 2004
Pattern Recognition—Classifiers
Fisher Discriminant Analysis
x2Maximize
21 22 2
1 2
( )m mσ σ
−+
x1
Pattern Recognition for VisionFall 2004
Pattern Recognition—Classifiers
Linear Support Vector Machines
1( )
N
i i ii
f sign y bα=
= ⋅ −
∑x x xMaximize margin d
ix
Pattern Recognition for VisionFall 2004
Pattern Recognition—Classifiers
Non-linear Support Vector Machines
x1
x2
Input Space
x*1
x*2
)(* xx Φ=
Feature Space
1( ) ( , ) , ( , ) ( ) ( )
N
i i i i ii
f sign y K b Kα=
= − = Φ Φ
∑x x x x x x x
Pattern Recognition for VisionFall 2004
Vision—Biological Object Recognition
Topics
•Visual Cortex•Hierarchical Processing•Scale Invariance •MAX Model for Object Recognition
Pattern Recognition for VisionFall 2004
Vision—Biological Object Recognition
The Visual System Simplified
Ventral stream:What?
Figure 1 in: Ungerleider, L., et. al. "A neural system for human visual working memory." Proceedings of the National Academy of Sciences 95 (February 1998): 883-890. Copyright 1998 National Academy of Sciences, U.S.A.
Pattern Recognition for VisionFall 2004
Vision—Biological Object Recognition
From Small and Simple to Big and Complex
Max’s stuffV1V4
ITC
modified from Ungerleider and Haxby, 1994
IT cells:Object specific
Hubel & Wiesel, 1959
Simple cells:Orientation of bars
Image removed due to copyright considerations.See: Hubel, and Weisel. "Receptive fields of single neuronsin the cat's striate cortex." Journal of Physiology 148 (1959): 574-951.
Image removed due to copyright considerations. See:Ungerleider, and Haxby. "'What' and 'where' in the human brain." Current Opinion in Neurobiology 4, no. 2 (1994): 157-165.
Pattern Recognition for VisionFall 2004
Vision—Biological Object Recognition
Hierarchical Processing: From Simple to Complex Features
Figure 1 in: Wersing, H., and E. Korner. "Learning Optimized Features for Hierarchical Models of Invariant Object Recognition." Neural Computation 15, no. 7 (2003): 1559-1558. MIT Press Journals. Courtesy of ________________MIT Press Journals. Used with permission.
Pattern Recognition for VisionFall 2004
Applications—Morphable Models
Topics
•2D MMs of facical components•2D MMs for facial animation
•3D MMs of faces•Modifying faces in the MM space
Pattern Recognition for VisionFall 2004
Applications—Morphable Models
2D Morphable Models for Facial Animation“Air” “Badge”
VideoDatabase
Visual SpeechProcessing
“Badge”
•Video realism•Machine learning
1I
2I 3I
4I
2C 3C
4C
Buildinga 2D MM
From Figure 1 in: Ezzat, Geiger, and Poggio. "Trainable Videorealistic Speech Animation."Proceedings of SIGGRAPH 2002, San Antonio, TX. Courtesy of authors. Used with permission.
Pattern Recognition for VisionFall 2004
Applications—Morphable Models
2D Morphable Models for Facial Animation
From Figure 10 in: Ezzat, Geiger, and Poggio. "Trainable Videorealistic Speech Animation."Proceedings of SIGGRAPH 2002, San Antonio, TX. Courtesy of authors. Used with permission.
Pattern Recognition for VisionFall 2004
Applications—Morphable Models
Generating 3D Face Models with MM
FaceImages
3D FaceModel
Morphing Space
Courtesy of Maxmillian Riesen-Huber. Used with permission.
Pattern Recognition for VisionFall 2004
Applications—Morphable Models
Modifying Faces in the MM Space
NovelImages
Figures removed due to copyright considerations. Please see: Figures from Vetter, T., and V. Blanz. "A Morphable Model for the Synthesis
of 3D Faces." Proceedings of SIGGRAPH (1999).
Pattern Recognition for VisionFall 2004
Applications—Object Detection & Recognition
Topics
•Face detection & recognition•Pedestrian detection•Feature extraction •Classification
Pattern Recognition for VisionFall 2004
Applications—Object Detection & RecognitionObject Detection
Search for faces atdifferent resolutions and locations
Feature vector (x1, x2 ,…, xn)
Classifier
Off-line training
Face examples
Non-face examples
Feature Extraction
Pixel pattern
Classification Result
Photograph by MIT OCW.
Photograph by MIT OCW.
Pattern Recognition for VisionFall 2004
Applications—Object Detection & Recognition
Object Recognition
Feature Extraction
Feature vector
Classifier
Face examples of different persons
A B
C D
Off-line training Identity of Person
Pixel pattern
Single image of a face
A