Paper
23 June 1993 Parametric eigenspace representation for visual learning and recognition
H. Murase, Shree K. Nayar
Author Affiliations +
Abstract
We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem as one of matching visual appearance rather than shape. The appearance of an object in a two- dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties of an object and are constant, pose and illumination vary from scene to scene. We present a new compact representation of object appearance that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This large image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a hypersurface. Given an unknown input image, the recognition system projects the image onto the eigenspace. The object is recognized based on the hypersurface it lies on. The exact position of the projection on the hypersurface determines the object's pose in the image. We have conducted experiments using several objects with complex appearance characteristics. We conclude with a discussion on various issues related to the learning and recognition techniques proposed in the paper.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
H. Murase and Shree K. Nayar "Parametric eigenspace representation for visual learning and recognition", Proc. SPIE 2031, Geometric Methods in Computer Vision II, (23 June 1993); https://doi.org/10.1117/12.146641
Lens.org Logo
CITATIONS
Cited by 18 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Machine vision

Visualization

Computer vision technology

Visual process modeling

Reflectivity

Image compression

RELATED CONTENT

Saliency detection based on manifold learning
Proceedings of SPIE (October 27 2013)
Contour detection combined with depth information
Proceedings of SPIE (December 14 2015)
Suggestive modeling for machine vision
Proceedings of SPIE (November 01 1992)
Detecting skin colors under varying illumination
Proceedings of SPIE (December 06 2011)

Back to Top