Dimensionality of illumination in appearance matching
- 23 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1326-1332 vol.2
- https://doi.org/10.1109/robot.1996.506890
Abstract
Appearance matching was recently demonstrated as a robust and efficient approach to 3D object recognition and pose estimation. Each object is represented as a continuous appearance manifold in a low-dimensional subspace parametrized by object pose and illumination direction. Here, the structural properties of appearance manifolds are analyzed with the aim of making appearance representation efficient in off-line computation, storage requirements, and online recognition time. In particular, the effect of illumination on the structure of the appearance manifold is studied. It is shown that for an ideal diffused surface of arbitrary texture, the appearance manifold is linear and three dimensional. This enables the construction of the entire illumination manifold from just three images of the object taken using linearly independent light sources. This result is shown to hold even for illumination by multiple light sources and for concave surfaces that exhibit inter-reflections. Finally, a simple but efficient algorithm is presented that uses just three manifold points for recognizing images taken under novel illuminations.Keywords
This publication has 12 references indexed in Scilit:
- Real-time 100 object recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning, positioning, and tracking visual appearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Face recognition using eigenfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Generalization of the Lambertian model and implications for machine visionInternational Journal of Computer Vision, 1995
- Visual learning and recognition of 3-d objects from appearanceInternational Journal of Computer Vision, 1995
- Illumination planning for object recognition in structured environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Shape from interreflectionsInternational Journal of Computer Vision, 1991
- Surface reflection: physical and geometrical perspectivesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Color and Grassmann-Cayley coordinates of shapePublished by SPIE-Intl Soc Optical Eng ,1991
- Photometric Method For Determining Surface Orientation From Multiple ImagesOptical Engineering, 1980