Optimal Features ASM Texture description based on Taylor series Grids centered at the landmarks for local analysis Non linear classifier (kNN) for inside-outside labeling 0 0 0 0 ) ( ) ( ! ) ( ) ( x x x x n x f x f n n insid e outsi de 1 2 1 B. van Ginneken, A.F. Frangi, J.J. Staal, B.M. ter Haar Romeny, and M.A. Viergever (2002) IEEE Transactions on Medical Imaging, 21(8):924–933
Optimal Features ASM
Feb 14, 2016
Texture description based on Taylor series Grids centered at the landmarks for local analysis Non linear classifier (kNN) for inside-outside labeling. outside. inside. 2. 1. Optimal Features ASM . - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Optimal Features ASM
Texture description based on Taylor series
Grids centered at the landmarks for local analysis
Non linear classifier (kNN) for inside-outside labeling
0
00
0)(
)(!
)()(
xx
xxnxfxf
n
n
inside
outside
1 2
1
B. van Ginneken, A.F. Frangi, J.J. Staal, B.M. ter Haar Romeny, and M.A. Viergever (2002)IEEE Transactions on Medical Imaging, 21(8):924–933
Optimal Features ASM Face is too complex for the proposed
labeling Thin zones generate profile variations Classes unbalance in high curvature
points kNN slow (set dependent) Image features dependent on rotation
1 2
2
Invariant Optimal Features ASM1 2
3
F.M. Sukno, S. Ordas, C. Butakoff, S. Cruz, and A.F. FrangiIEEE Transactions on Pattern Analysis and Machine Intelligence, 29(7):1105–1117
Invariant Optimal Features ASM Distance-based labeling
1 2 3 4 5 6 7-2.5
-2
-1.5
-1
-0.5
0
0.5
1
1.5
2R = 1 L = 18
1 2 3 4 5 6 7-2
-1.5
-1
-0.5
0
0.5
1
1.5R = 1 L = 18
180 profiles of man and women with IOF-ASM
1 2
0 2 4 6 8 10 12 14-0.5
-0.4
-0.3
-0.2
-0.1
0
0.1
0.2
0.3
0.4
0 2 4 6 8 10 12 14-0.25
-0.2
-0.15
-0.1
-0.05
0
0.05
0.1
0.15
0.2
4
Invariant Optimal Features ASM1 2
Multi-valued neuron classifier Single neuron Very fast
Appropriate combination of derivatives allows for invariance to rigid transformations
i q s
q s
i
0
1
k-1
k-2
Z
5
Segmentation tests1 2
6
Experiments on 3400+
images
Point to curve errorPoint to point error
IOFASM vs ASMDataset
Images
Error
AR 532 - 33.2 %
Equinox
546 - 25.2 %
XM2VTS
2360 - 33.8 %
1 2
7
IOFASM vs ASM
ASM IOF-ASM
1 2
8
Identity Verification: TextureBased on texture
Eigenfaces-like approach from the segmentation results
1 2
9
Identity Verification: Texture1 2
10
Related work1 2
11
Conclusions on IOF-ASM1 2
By using more elaborate descriptions of the texture it is possible to increase the accuracy of ASMs IOF-ASM provides a generic framework Features are optimized for every landmark
Allows for a trade off between accuracy and speed Feature selection: –15% error / –50% time
About 30% more accurate than ASM in facial feature localization Derives in better identification rates
Invariant to in-plane rotations 12
Out-of-plane Rotations Environment
constraints● Surveillance
systems● Car driver images
ASM:● Similarity does not
remove 3D pose ● Multiple-view
database Other approaches
● Non-linear models● 3D models: multiple
views
AV@CAR Database
1 2 3
13
Related Documents
