epitome
DESCRIPTION
Spring 2004, CS7636 Computational Perception. Epitome. Ji Soo Yi and Woo Young Kim Instructor: Prof. James Rehg April 27, 2004. CONTENTS. Introduction Epitomic Image Experiment Results & Conclusion Future direction. Edited by Woo Young and Ji Soo. Introduction(1). - PowerPoint PPT PresentationTRANSCRIPT
EpitomeEpitome
Ji Soo Yi and Woo Young Kim
Instructor: Prof. James Rehg
April 27, 2004.
Spring 2004, CS7636 Computational Perception
CONTENTS
Introduction
Epitomic Image
Experiment
Results & Conclusion
Future direction
Edited by Woo Young and Ji Soo
Introduction(1)
Image representative modelFeature-based
Geometric approach
Template-based Standard Euclidian error norms Eigen spaces
Color histogram-based
Edited by Woo Young and Ji Soo
Introduction(2)
Epitomic image analysisWhat is Epitome?
The miniature, condensed version of image. Still consists of most constitutive elements. Use a probabilistic measure of similarities. Shape epitome and appearance epitome.
Edited by Woo Young and Ji Soo
Introduction(3)
Epitomic image analysisGraphical model of epitomic analysis
Edited by Woo Young and Ji Soo
Es
MS1S2
I
Emappearance
epitome
shape
epitome
I=M*S1+(1-M)*S2 + noise
Introduction(4) Epitomic image analysis
Probabilistic framework
Edited by Woo Young and Ji Soo
epitome
e = (,)
M,N
Patch Zk = {zi,k}, zi,k= xi
Input image X
Patch Zn
Me, Ne
Tk
Tn
Introduction(5) Epitomic image analysis
EM algorithm to extract an epitomic image
Edited by Woo Young and Ji Soo
E step:
M step:
Epitomic Image (1)
Edited by Woo Young and Ji Soo
Original image Epitomic image
Epitomic Image (2)
Edited by Woo Young and Ji Soo
Input imageEpitomic image
Experiment (1)
Edited by Woo Young and Ji Soo
Epitomic Modeling
Face Detection
Comparison with PCA Analysis
Experiment (2)
Edited by Woo Young and Ji Soo
Epitomic Modeling
Training data – a set of face images
Each image : 100 by 75Epitomic image: 32 by 32
Epitomic image
Experiment (3)
Edited by Woo Young and Ji Soo
Epitomic Modeling
Training data – a synthetic image by tiling face images
100 by 75 pixels for each image
1000 by 375 pixels for total
75 by 75 pixels
Experiment (4)
Edited by Woo Young and Ji Soo
Face Detection
Histogram and clustering
Experiment(5)
Edited by Woo Young and Ji Soo
Face Detection
Patch matching – face image
High log likelihood – good match Low log likelihood - poor match
Experiment(6)
Edited by Woo Young and Ji Soo
Face Detection
Patch matching – non face image
Low log likelihood – good match High log likelihood - poor match
Experiment(7)
Detection rate of PCA analysis
0.92
0.660.620
0.00
training face testing face
dete
ctio
n ra
te
Rigid
Non-Rigid
Edited by Woo Young and Ji Soo
Comparison with PCA analysis – PCA
Rigid data
Non-Rigid data
Experiment(8)
Detection rate of Epitomic analysis
0.700 0.7000.725 0.725
face nonface
Dete
ctio
n ra
te
Rigid
Non-Rigid
Edited by Woo Young and Ji Soo
Comparison with PCA analysis – Epitome
Rigid data
Non-Rigid data
Results & Conclusion
Edited by Woo Young and Ji Soo
Epitomic image modeling
Parameter settings
Comparison with PCA Analysis
Statistics
Future direction
Edited by Woo Young and Ji Soo
Computational time saving
Shape epitome
Other applications