Download:
by Peter N. Belhumeur, David J. Kriegman
IJCV
http://www1.cs.columbia.edu/~ravir/6998/papers/ijcv98.pdf
Add To MetaCart
Abstract:
Abstract. The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then – in theory – the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources, shadows, and color. We prove that the set of n-pixel monochrome images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IR n and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IR n. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation.
Citations
|
1849
|
Eigenfaces for recognition
– Turk, Pentland
- 1991
|
|
1509
|
Convex Analysis
– Rockafellar
- 1970
|
|
1161
|
Robot Vision
– Horn
- 1986
|
|
809
|
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
– Belhumeur, Hespanha, et al.
- 1997
|
|
779
|
Visual learning and recognition of 3-D objects from appearance
– Murase, Nayar
- 1995
|
|
495
|
View-Based and Modular Eigenspaces for Face Recognition
– Pentland, Moghaddam, et al.
- 1994
|
|
456
|
Example-based learning for view-based human face detection
– Sung, Poggio
- 1998
|
|
384
|
Recognition by linear combinations of models
– Ullman, Basri
- 1991
|
|
308
|
Low-dimensional procedure for the characterization of human faces
– Sirovich, Kirby
- 1987
|
|
239
|
Theory for off-specular reflection from roughened surfaces
– Torrance, Sparrow
- 1967
|
|
172
|
Face Recognition: The Problem of Compensating for Changes in Illumination Direction
– Adini, Moses, et al.
- 1997
|
|
99
|
A Low-Dimensional Representation of Human Faces For Arbitrary Lighting Conditions
– Hallinan
- 1994
|
|
88
|
Spectral sharpening: sensor transformations for improved color constancy
– Finlayson, Drew, et al.
- 1994
|
|
69
|
Geometry and photometry in 3D visual recognition
– Shashua
- 1992
|
|
66
|
Generalization of the Lambertian model and implications for machine vision
– Oren, Nayar
- 1995
|
|
61
|
The bas-relief ambiguity
– Belhumeur, Kriegman, et al.
- 1999
|
|
60
|
Shape from interreflections
– Nayar, Ikeuchi, et al.
- 1991
|
|
60
|
Body plans
– Forsyth, Fleck
- 1997
|
|
52
|
Bidirectional reflection distribution function expressed in terms of surface scattering modes
– Koenderink, Doorn, et al.
- 1996
|
|
45
|
Photometric Stereo under a Light Source with Arbitrary Motion
– Hayakawa
- 1994
|
|
43
|
5+/-2 eigenimages suffice: An empirical investigation of low-dimensional lighting models
– Epstein, Hallinan, et al.
- 1995
|
|
34
|
Reflections on shading
– Forsyth, Zisserman
- 1991
|
|
23
|
Low-dimensional procedure for the characterization of human faces
– Sirovitch, Kirby
- 1987
|
|
22
|
Detection of diffuse and specular interface reflections and inter-reflections by color image segmentation
– Bajcsy, Lee, et al.
- 1996
|
|
18
|
fitting with missing data: Applications to structure from motion and characterizing intensity images
– Linear
- 1997
|
|
12
|
Image segmentation and reflection analysis through color
– Klinker, Shafer, et al.
- 1988
|
|
11
|
Dimensionality of illumination in appearance matching
– Nayar, Murase
- 1996
|
|
8
|
Learning and recognizing objects using illumination subspaces
– Epstein, Yuille, et al.
- 1996
|
|
8
|
A framework for the construction of reflectance maps for machine vision
– TAGARE, DEFIGUEIREDO
- 1993
|
|
6
|
5 \Sigma 2 Eigenimages Suffice: An Empirical Investigation of Low-Dimensional Lighting Models
– Epstein, Hallinan, et al.
- 1995
|
|
3
|
A ray-based computational model of light sources and illumination
– Langer, Zucker
- 1995
|
|
3
|
Shape from interre ections
– Nayar, Ikeuchi, et al.
- 1991
|
|
2
|
Generic Surface Interpretation : Observability Model
– Binford
- 1991
|
|
2
|
5+/-2 eigenimages su ce: An empirical investigation of lowdimensional lighting models
– Epstein, Hallinan, et al.
- 1995
|
