© The Institution of Engineering and Technology
The authors apply partial least squares regression to predict three-dimensional (3D) face shape from a single image. PLS describes the relationship between independent (intensity images) and dependent (3D shape) variables by seeking directions in the space of independent variables that are associated with large variations in the space of dependent variables. We use this idea to construct statistical models of intensity and 3D shape that capture strongly linked variations in both spaces. This decomposition leads to the construction of two different models that capture common variations in 3D shape and intensity. Using the intensity model, a set of parameters is obtained from out-of-training intensity examples. These intensity parameters can then be used directly in the 3D shape model to approximate facial shape. Experiments show that prediction is achieved with reasonable accuracy, improving results obtained through canonical correlation analysis.
References
-
-
1)
-
Reiter, M., Donner, R., Langs, G., Bischof, H.: `3d and infrared face reconstruction from RGB data using canonical correlation analysis', Proc. 18th ICPR'06, 2006.
-
2)
-
Lei, Z., Bai, Q., He, R., Li, S.Z.: `Face shape recovery from a single image using CCA mapping between tensor spaces', Proc. IEEE CVPR'08, 2008, p. 1–7.
-
3)
-
Blanz, V., Vetter, T.: `A morphable model for the synthesis of 3d faces', SIGGRAPH'99: Proc. 26th Ann. Conf. Computer Graphics and Interactive Techniques, 1999, New York, NY, USA, p. 187–194.
-
4)
-
A. Jognston ,
H. Hill ,
N. Carman
.
Recognising faces: effects of lightning direction, inversion and brightness reversal.
Perception
,
365 -
375
-
5)
-
H. Hotelling
.
Relations between two sets of variates.
Biometrika
,
321 -
377
-
6)
-
Kemelmacher, I., Basri, R.: `Molding face shapes by example', Proc. Eur. Conf. Computer Vision, 2006.
-
7)
-
P. Belhumeur ,
D. Kriegman
.
What is the set of images of an object under all possible lighting conditions?.
Int. J. Comput. Vis.
,
3 ,
245 -
260
-
8)
-
J. Atick ,
P. Griffin ,
N. Redlich
.
Statistical approach to shape from shading: reconstruction of three-dimensional face surfaces from single two-dimensional images.
Neural Comput.
,
1321 -
1340
-
9)
-
H. Wold
.
Estimation of principal components and related models by iterative least squares.
Multivariate Anal.
-
10)
-
V. Blanz ,
T. Vetter
.
Face recognition based on fitting a 3d morphable model.
IEEE Trans. Pattern Anal. Mach. Intell.
,
9 ,
1063 -
1074
-
11)
-
W.A.P. Smith ,
E.R. Hancock
.
Recovering facial shape using a statistical model of surface normal direction.
IEEE Trans. Pattern Anal. Mach. Intell.
,
12 ,
1914 -
1930
-
12)
-
S. Sarkar
.
3D face database.
-
13)
-
L. Hoegaerts ,
J.A.K. Suykens ,
J. Vandewalle ,
B. De Moor
.
Subset based least squares subspace regression in RKHS.
Neurocomputing
,
293 -
323
-
14)
-
I. Frank ,
J. Friedman
.
A statistical view of some chemometrics regression tools.
Technometrics
,
2 ,
109 -
135
-
15)
-
X. Wu ,
D. Li ,
J. Gang ,
Z. Zhou
.
A structured light-based system for human heads.
Opt. Laser Technol.
,
5 ,
387 -
391
-
16)
-
B.K.P. Horn ,
M.J. Brooks
.
(1989)
Shape from shading.
-
17)
-
L. Sirovich ,
M. Kirby
.
Low-dimensional procedure for the characterization of human faces.
J. Opt. Soc. Am.
,
519 -
524
-
18)
-
A. Ghosh ,
T. Hawkins ,
P. Peers ,
S. Frederiksen ,
P. Debevec
.
Practical modeling and acquisition of layered facial reflectance.
ACM Trans. Graph.
,
5 ,
1 -
10
-
19)
-
M. Castelán ,
W. Smith ,
E. Hancock
.
A coupled statistical model for face shape recovery from brightness images.
IEEE Trans. Image Process.
,
4 ,
1139 -
1151
-
20)
-
A. Georghiades ,
D. Belhumeur ,
D. Kriegman
.
From few to many: illumination cone models for face recognition under variable lighting and pose.
IEEE Trans. Pattern Anal. Mach. Intell.
,
634 -
660
-
21)
-
A. Van Den Wollenberg
.
Reduncancy analysis: an alternative to canonical correlation analysis.
Psychometrika
,
207 -
219
-
22)
-
Borga, M., Landelius, T., Knutsson, H.: `A unified approach to PCA, PLS, MLR and CCA', Number LiTH-ISY-R-1992, Technical Report, .
-
23)
-
P. Geladi ,
B. Kowalski
.
Partial least squares regression: a tutorial.
Anal. Chim. Acta
,
1 -
17
-
24)
-
R.T. Frankot ,
R. Chellappa
.
A method for enforcing integrability in shape from shading algorithms.
IEEE Trans. Pattern Anal. Mach. Intell.
,
438 -
451
-
25)
-
Cootes, T., Edwards, G., Taylor, C.: `Active appearance models', Proc. Eur. Conf. Computer Vision, 1998, p. 484–498.
-
26)
-
H. Abdi
.
Partial least square regression (pls regression).
Encycl. Meas. Stat.
,
740 -
744
-
27)
-
P.L. Worthington ,
E.R. Hancock
.
New constraints on data-closeness and needle map consistency for shape-from-shading.
IEEE Trans. Pattern Anal. Mach. Intell.
,
12 ,
1250 -
1267
-
28)
-
R. Donner ,
M. Reiter ,
G. Langs ,
P. Peloscheck ,
H. Bischof
.
Fast appearance model search using canonical correlation analysis.
IEEE Trans. Image Pattern Anal. Mach. Intell.
,
10 ,
1690 -
1694
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2008.0060
Related content
content/journals/10.1049/iet-cvi.2008.0060
pub_keyword,iet_inspecKeyword,pub_concept
6
6