Title: Learning the Appearance of Faces for an automated Image Analysis'
1Learning the Appearance of Faces for an automated
Image Analysis.
Thomas Vetter
University of Basel
Switzerland
http//informatik.unibas.ch
2Change Your Image ...
3Analysis by Synthesis
Computer Graphics can help to solve Computer
Vision!
4Analysis by Synthesis
Image
3D World
Image Description
5(No Transcript)
6(No Transcript)
7Synthesis of Faces
Modeler
Result
Input Image
8Database of 3D Faces
9Approach Example based modeling of faces
2D Image 2D Face
Examples
w1 w2
w3 w4
. . .
10Cylindrical Coordinates
red(h,f) green(h,f) blue(h,f)
radius(h,f)
11Morphing 3D Faces
1
__
2
12Shape and Texture Vectors
Example i
Reference Head
13Correspondence A two step process!
- Correspondence between
- two examples ( Optical Flow like algorithms).
- many examples ( Morphable Model )
14Bootstrapping the Morphable Model
Reference Scan
15Vector space of 3D faces.
- A Morphable Model can generate new faces.
a1 a2 a3
a4 . . .
b1 b2 b3
b4 . . .
16Manipulation of Faces
17Continuous Modeling in Face Space
18Modelling the Appearance of Faces
A face is represented as a point in face space.
- Which directions code for specific attributes ?
19Learning from Labeled Example Faces
Fitting a regression function
20Facial Attributes
Gender
Original
213D Shape from Images
Input Image
3D Head
22Matching a Morphable 3D-Face-Model
- R Rendering Function
- Parameters for Pose, Illumination, ...
-
- Find optimal a, b, r !
23Automated Parameter Estimation
150 shape coefficients ai 150 texture
coefficients bi
head position head orientation focal length
- Ambient intensity, color
- Parallel intensity, color, direction
- Color contrast, gains, offsets
24Error Function
Minimize Image Differences
Maximize prior probability
25Image Formation at each Vertex k
bi
ai
263D Shape from an Image
Input Image
27Texture
Texture Extraction
28Phong Illumination
- Ambient light ir, amb ig, amb ib, amb
- Parallel light ir, dir ig, dir ib, dir
from direction l - Lambertian shading and specular reflections
- Reflectivity at vertex i Ri Gi Bi ,
shininess s - surface normal ni , reflected ray ri
- vi normalized difference of position of camera
and vertex
29Illumination-Corrected Texture Extraction
Vertex i
Reflectance Ri Gi Bi
30(No Transcript)
31Recognition from Images
323D Computer Graphics
33Optimization steps
Original
7 Feature PointsManually
34Optimization steps
Original
StartAutomated Process
35Optimization steps
Original
Fit to Featuresautomatically
36Optimization steps
Fit Illuminationautomatically
Original
37Reconstruction
Fitting the 4 individual face segments
automatically
Original
4.5 min on 2GHz Pentium 4
38CMU-PIE database
39Identification from Model Coefficients
Gallery
40Correct Identification 1 out of 68 ()
gallery
profile
side
front
probe
99.8
front
99.9
side
98.3
profile
total
CMU-PIE database 4488 images of 68 individuals
3 poses x 22
illuminations 66 images per individual
41Image Preprocessing for FRVT 2002
42Image Preprocessing for FRVT 2002
43Image Preprocessing for FRVT 2002
44Segmenting hair a general requirement !
45Try New Hairstyles
3D Shape and Texture
46More Hairstyles
3D Shape and Texture
3D Angle, Position Illumination, Foreground,
Background
47Novel Hairstyles
Customer
Hairstyle
48V. Blanz, C. Basso, T. Poggio T.
Vetter Reanimating Faces in images and Video
Proc. of Eurographics 2003
49Facial Attributes I Gender
male
female
50Experiment I Hypotheses
Not only the gender but also the facial features
of a person affect gender-stereotypic
attributions.
H1 - Subjects rate the leadership aptitude of...
a) a man higher than of a woman. b) a
masculine person higher than of a feminine person.
H2 - Subjects rate the social competence
of... a) a woman higher than of a man. b) a
feminine person higher than of a masculine person.
51Experiment I Results
feminine
masculine
Mean SC Mean LA
male
4.66 4.48
female
4.7 4.09
Mean SC 4.77 4.58Mean LA 4.25 4.32
52References
http//informatik.unibas.ch
A Morphable Model for the Synthesis of 3D Faces.
Blanz, V. and Vetter, T. SIGGRAPH'99
Conference Proceedings, pp. 187-194, 1999. A
bootstrapping algorithm for learning linear
models of object classes. T. Vetter, M.J. Jones
and T. Poggio, IEEE Conference on Computer
Vision and Pattern Recognition -- CVPR'97, pp
40-46, Puerto Rico, USA, 1997. A Morphable
Model for face Recognition Volker Blanz and
Thomas Vetter IEEE PAMI (9), 2003
53Acknowledgement
Volker Blanz Sami Romdhani Curzio Basso