© The Institution of Engineering and Technology
Multiple light source detection has many applications in image synthesis and augmented reality. Current techniques can provide accurate results but have limited applicability in real-life scenarios where interaction with the scene is not possible. The authors provide a statistical framework for multiple light source detection that relies on the common features of objects belonging to a particular class and illustrate it using the class of human faces. Experiments with real data demonstrate that a light distribution with up to three light sources can be detected within 13° mean error. Application of the proposed framework to the problem of 3D reconstruction from multiple images under arbitrary lighting demonstrates the effectiveness of the framework compared with current techniques.
References
-
-
1)
-
Liu, C., Wechsler, H.: `Enhanced Fisher linear discriminant models for face recongnition', Int. Conf. on Pattern Recognition, August 1998.
-
2)
-
Zhang, L., Samaras, D.: `Face recognition under variable lighting using harmonic image exemplars', CVPR, 2003, I, p. 19–25.
-
3)
-
Sato, I., Sato, Y., Ikeuchi, K.: `Illumination distribution from brightness in shadows: adaptive estimation of illumination distribution with unknown reflectance properties in shadow regions', Int. Conf. Computer Vision, 1995, 2, p. 875–882.
-
4)
-
Kemelmacher, I., Basri, R.: `Molding face shapes by example', ECCV'06, May 2006, 1, p. 277–288.
-
5)
-
Debevec, P.E.: `Rendering synthetic objects into real scenes: Bridge traditional and image-based graphics with global illumination and high dynamic range photography', SIGGRAPH 98, July 998, p. 189–198.
-
6)
-
A.P. Pentland
.
Finding the illuminant direction.
J. Opt. Soc. Am.
,
448 -
455
-
7)
-
Schemer, Y.Y., Nayar, S.K., Belhemeur, P.N.: `A theory of multiplexed illumination', 9thIEEE Inter. Conf. on Computer Vision (ICCV'03), 2003, 2, p. 808–815.
-
8)
-
Nishino, K., Nayar, S.K.: `Eyes for relighting', SIGGRAPH, 2004, 23, p. 704–711.
-
9)
-
Marchener, S.R., Greenberg, D.P.: `Inverse lighting for photography', 5thColor Imaging Conf., Society for Imaging Science and Technology, 1997.
-
10)
-
T. Vetter ,
T. Poggio
.
Linear object classes and image synthesis from a single example image.
IEEE Trans. Pattern Anal. Mach. Intell.
,
7 ,
733 -
742
-
11)
-
Sim, T., Basker, S., Bast, M.: `The CMU pose, illumination, and expression (PIE) database', Proc. 5th Int. Conf. on Automatic Face Gesture Recognition, 2002.
-
12)
-
T. Sim ,
T. Kanade
.
(2001)
Illuminating the face, Tech. Rep. CMU-RI-TR-01-31..
-
13)
-
Lee, K.C., Ho, J., Kriegman, D.: `Nine points of light: acquiring subspaces for faces recognition under variable lighting', Proc IEEE Conf. Computer Vision and Pattern Recognition, 2001.
-
14)
-
A.S. Georghiades ,
P.N. Belhumeur ,
D.J. Kriegman
.
From few to many: illumination cone models for face recognition under variable lighting and pose.
IEEE Trans. Pattern Anal. Mach. Intell.
,
6 ,
643 -
660
-
15)
-
P. Belhumeur ,
J. Hespanha ,
D. Kriegman
.
Eigenfaces vs fusherfaces: recognition using class specific linear projection.
IEEE Trans. Pattern Anal. Mach. Intell.
,
7 ,
711 -
720
-
16)
-
Georghiades, A.S., Kriegman, D.J., Belhumeur, P.N.: `Illumination cones for recognition under variable lighting: faces', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 1998, p. 52–58.
-
17)
-
R.O. Duda ,
P.E. Hart
.
(1973)
Pattern classification and scene analysis.
-
18)
-
S.C. Kee ,
K.M. Lee ,
S.U. Lee
.
Illumination invariant face recognition using photometric stereo.
IEICE Trans. Inf. Syst.
,
7 ,
1466 -
1474
-
19)
-
K.E. Torrance ,
E.M. Sparrow
.
Theory for off-specular reflection from roughened surface.
J. Opt. Soc. Am.
,
1105 -
1114
-
20)
-
Cootes, T., Walker, K., Taylor, C.: `View-based active appearance models', 4thInt. Conf. on Automatic Face and Gesture Recognition, 2000, p. 227–232.
-
21)
-
B.T. Phong
.
Illumination for computer generated images.
Commun. ACM
,
311 -
317
-
22)
-
Bouganis, C.-S., Brookes, M.: `Class-based multiple light detection: an application to faces', British Machine Vision Conf., 2003, 1, p. 113–122.
-
23)
-
A. Shashua
.
On photometric issues in 3d visual recognition from a single 2d image.
Int. J. Comput. Vis.
,
99 -
122
-
24)
-
Cyberwarehttp://www.cyberware.com/(1999).
-
25)
-
C.-S. Bouganis ,
M. Brookes
.
Mulitple light source detection.
IEEE Trans. Pattern Anal. Mach. Intell.
,
4 ,
509 -
514
-
26)
-
R. Basri ,
D. Jacobs ,
I. Kemelmacher
.
Photometric stereo with general, unknown lighting.
Int. J. Comput. Vis.
,
3 ,
239 -
257
-
27)
-
Yang, J., Yu, H., Kunz, W.: `An Effcient LDA algorithm for face recognition', 6thInt. Conf. on Control, Automation, Robotics and Vision (ICARCV 2000), 2000.
-
28)
-
Debevec, P., Hawkins, T., Tchou, C., Duiker, H.P., Sarokin, W., Sagar, M.: `Acquiring the reflectance field of a human face', SIGGRAPH 00, 2000, p. 145–156.
-
29)
-
I.T. Jolliffe
.
(1986)
Principle component analysis.
-
30)
-
K. Fukunaga
.
(1991)
Introduction to statistical pattern recognition.
-
31)
-
T. Riklin-Raviv ,
A. Shashua
.
The quotient image: class-based re-rendering and recognition with varying illuminations.
IEEE Trans. Pattern Anal. Mach. Intell.
,
2 ,
129 -
131
-
32)
-
R. Basri ,
D.W. Jacobs
.
Lambertian reflectance and linear subspaces.
IEEE Trans Pattern Anal. Mach. Intell.
,
2 ,
218 -
233
-
33)
-
J.-H. Jiang ,
R. Tsenkova ,
Y. Ozaki
.
Principal discriminant variate method for classification of multicollinear data: principle and applications.
Anal. Sci.
,
i471 -
i474
-
34)
-
W.Y. Zhao ,
R. Chellappa
.
Symmetric shape-from-shading using self-ratio image.
Int. J. Comput. Vis.
,
1 ,
55 -
75
-
35)
-
P.N. Belhumeur ,
D.J. Kriegman
.
What is the set of images of an object under all possible lighting conditions?.
Proc. IEEE Conf. on Computer Vision and Pattern Recognition
,
270 -
277
-
36)
-
Tsumura, N., Dang, M.N., Makino, T., Miyake, Y.: `Estimating the directions to light sources using images of eye for reconstructing 3D human face', IS&T/SIDs 11 Color Imaging Conf., 2003, p. 77–81.
-
37)
-
Kovesi, P.: `Shapelets correlated with surface normals produce surfaces', IEEE Int. Conf. on Computer Vision, 2005, 2, p. 994–1001.
-
38)
-
R. Brunelli
.
Estimation of pose and illuminant direction for face processing.
Image Vis. Comput.
,
10 ,
741 -
748
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi_20065001
Related content
content/journals/10.1049/iet-cvi_20065001
pub_keyword,iet_inspecKeyword,pub_concept
6
6