Documente Academic
Documente Profesional
Documente Cultură
• 40 persons
•10 images per
person
•Different times,
expressions,
lightning and
details
(glasses)
Yale Database
• 165 images of 15 individuals. There are 11
images per subject, one per different facial
expression or configuration: center-light,
w/glasses, happy, left-light, w/no glasses,
normal, right-light, sad, sleepy, surprised, and
wink.
Neural Networks: RBFNN
• Hock Koh et al approach
• Preprocessing:
– Detect the face
– Enhance the image
– Identify nose and boundaries
• Features: Radial grid centered on the
nose, value at each point: mean of region
Example of Radial Grid
Different area diameters - Radial grid size 6x12
6
-2
-4
-6
-6 -4 -2 0 2 4 6
Architecture
• Feed forward architecture, 3 layers
– Input layer NI nodes, fully connected to the hidden
layer
η×d2
– Hidden layer RBF σ =
2
− x −m 2
j i
g0 (x j ) = 1 g i ( x j ) = exp
η×d
2
0
λ01
λ0C λ02
xj1 y1
1 1 1
m1
λ21
xj2 y2
λ22
2 2 2
m2
λ2C
yC
xjI NC
NI
NH
mH
Input feature Classification
vector size classes
Training and classification
• Xj training vector
1 _ if _ x j ∈ yk
• Output: yk ( x j ) =
0 _ otherwise
C-1 comparisons
Running time SVM
• O(n2) for training
• O(n) for evaluating an input
• Bicego’s approach: for 100 classes, 10
minutes for training and 10 seconds for
classifying
– Matlab @ Intel Celeron 850 MHz
Comparison of different
approaches
Reference Feature # of Recognition Datbase Error Comment
Extraction features Method used (%)
Method
[2] Grid average 256 RBFNN own 2.9 Up to 25°
sampling variation in
direction
[3] PCA + Fisher 25 RBFNN ORL 1.92 Fast training
discriminant method
[1] PCA 10-100 SVM ORL 3