Title: Topic 5' Human Faces
1Topic 5. Human Faces
- Human face is extensively studied in vision.
Depending on the applications, there are a - long list of tasks 5
- Detection and Recognition
- Face detection (finding all faces
in a picture), facial feature detection (eyes,
lips, ), - Face localization (detecting a
single face in image), - Face recognition or
identification (from a database, classification) - Face authentication (verifying
claim, bank id), Age/gender recognition, - Face tracking (location and pose
over time) - Facical expression recognition
(affective states), aesthetic study. - Modeling and Photorealistic Synthesis
- Appearance models, deformable
templates, lighting models, facial action
units, - face hallucination (high
resolution from low resolution), - pose adjustment, image editing
(removing wrinkles, eye glass, red-eye etc.) - 3. Artistic rendering
- Sketch, portrait, caricature,
cartoon, painting,
2Face Image Databases
The CMU Rowley dataset
3Face Image Databases
The CMU Schneidrman and Kanade Dataset
4References.
1. P. Hallinan, G. Gordon, A. Yuille, P.
Giblin, and D. Mumford, 2D and 3D Patterns
of the Face, A.K. Peters, Ltd. Book
chapters 2-4. (handouts). 2. D.H. Ballard,
"Generaling the Hough transform to detect
arbitrary shapes", (in handbook). 3. P. Viola
and M. Jones, "Robust Real Time Object
Detection", 4. F. Fleuret and D. Geman, "
Coarse-to-fine face detection", IJCV
41(1/2),2001. 5. M.H. Yang, D. Kriegman, N.
Ahuja, Detecting faces in images, a survey,
PAMI vol.24,no.1, January, 2002. 6
T.F.Cootes, G.J. Edwards and C.J.Taylor. "Active
Appearance Models", ECCV 1998 7. C. Liu, S. C.
Zhu, and H. Y. Shum, "Learning inhomogeneous
Gibbs models of faces by minimax entropy", ICCV
2001. 8. Y. Tian, T. Kanade, and J. Cohn,
"Recognizing action units for facial expression
analysis" PAMI, Feb, 2001. 9. H.
Chen, Y. Q. Xu, H. Y. Shum, S. C. Zhu, and N. N.
Zhen, "Example-based facial sketch generation
with non-parametric sampling", ICCV 2001.
5Outline
- We proceed in three steps
- A survey on face detection and recognition
techniques - Mathematical models of face images
- 3. Face synthesis photorealistic and
non-photorealistic.
6Face Detection Methods 5
7Face vs non-face Clsutering
6 clusters in a 19 x19 space (Sung and Poggio)
8Distance Measure
D2
D1
For each input image, it measures two distances
for each cluster center D1 is the
Mahalanobis distance and D2 is the Euclidean
distance. Thus Sung and poggio have 2 x 6 x 2
24 features for classification in a multiple
layer perceptron.
9Deformable Face Template
Deformable face template by Fishler and
Elschlager 1973. M. Fishler and R. Elschlager,
The representation and matching of pictorial
structures, IEEE Trans. on Computer.
Vol.C-22, 67-92, 1973.
10Local Deformation and Global Transform
Geometric variations of faces (Hallinan, Yuille,
Mumford et al)
11Deformable Model of Facial Features
Eye template using parabolic curves by Yuille et
al 1989-92. A.L.Yuille, D. Cohen, and
P.Hallinan, Feature extraction from faces using
deformable templates, CVPR 89, IJCV 92.
We can derive meaningful diffusion equations from
the energy functionals.
12Upper Face Action Units
13Lower Face Action Units
14Templates for Various States
15Templates for Various States
16Features for Action Unit Recognition
17Classification from Feature Vector
18Recognition Rate
19Apparence Model Landmarks on a face
400 images each labeled with 122 points.
20Eigen-vectors for Geometry and Photometry
21Apparence Model
22Face Localization and Recognition
23A Linear HMM Model for Face
24Face Detection
25Sample of the 4D space
26Multi-scale Detection
27Edge Features
28Decision Tree
29Examples of Decision Trees
30Bounds Analysis
31Some Examples
32Face Prior Learning Experimental Details
- 83 key points defined on face
- 720 individuals with all kinds of types
- Dimension reduced to 33 by PCA
- 40000 samples drawn by the inhomogeneous Gibbs
sampler in each Monte Carlo integration - 50 features pursuit
- Total runtime about 5 days on a PIII 667, 256MB
PC
33Obs Syn Samples (1)
Observed faces
Synthesized faces without any features
34Synthesis Samples
Synthesized faces with 10 features
Synthesized faces with 20 features
35Synthesis Samples
Synthesized faces with 30 features
Synthesized faces with 50 features
3650 Observed Histograms
3750 Synthesized Histograms