Abstract
This paper describes an experimental investigation of the recognition performance of two approaches to the representation of objects for recognition. The first representation, generally known as appearance modelling, describes an object by a set of images. The image set is acquired for a range of views and illumination conditions which are expected to be encountered in subsequent recognition. This image database provides a description of the object. Recognition is carried out by constructing an eigenvector space to compute efficiently the distance between a new image and any image in the database. The second representation is a geometric description based on the projected boundary of an object. General object classes such as planar objects, surfaces of revolution and repeated structures support the construction of invariant descriptions and invariant index functions for recognition.
In this paper we present an investigation of the relative performance of the two approaches. Two objects, a planar object and a rotationally symmetric object are modelled using both approaches. In the experiments, each object is intentionally occluded by an unmodelled distractor for a range of viewpoints. The resulting images are submitted to two separate recognition systems. Appearance-based recognition is carried out by SLAM and recognition of invariant geometric classes by Lewis/Morse.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Beymer D., ‘Face Recognition Under Varying Pose', Proc CVPR, 756–761, 1994.
Craw I. and Cameron P., ‘Parametrizing images for recognition and reconstruction', Proc BMVC, 367–370, 1991.
Duda R.O. and Hart P.E., Pattern Classification and Scene Analysis, Wiley, 1973.
Forsyth D. and Zisserman A., ‘Reflections on shading', PAMI, 13, 7, 671–679, 1991.
Belhumeur N., Hespanha J. and Kriegman D., ‘Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection', Proc. ECCV, 45–58, 1996.
Lanitis A., Taylor C.J. and Cootes T.F., ‘A Unified Approach to Coding and Interpreting Face Images', Proc ICCV, 368–373, 1995.
Liu J.S., Mundy J.L., Forsyth D.A., Zisserman A. and Rothwell C.A., ‘Efficient Recognition of Rotationally Symmetric Surfaces and Straight Homogeneous Generalized Cylinders', Proc. CVPR, 1993.
Mukherjee D.P., Zisserman A. and Brady J.M., ‘Shape from symmetry—detecting and exploiting symmetry in affine images', Phil. Trans. R. Soc. Lond. A, 351, 77–106, 1995.
Mundy J.L. and Zisserman A. Geometric Invariance in Computer Vision, MIT Press, 1992.
Murakami H. and Kumar V., ‘Efficient calculation of primary images from a set of images,’ IEEE Transactions on Pattern Analysis and Machine Intelligence, 4, 511–515, 1982.
Murase H. and Nayar S.K., ‘Visual Learning and Recognition of 3-D Objects from Appearance'. IJCV, 14, 1, 1995.
Murase H. and Nayar S., ‘Illumination Planning for Object Recognition Using Parametric Eigenspaces’ IEEE Trans. PAMI, 16, 12, 1219–1227, 1995.
Murase H. and Nayar S., ‘Image Spotting of 3D Objects Using the Parametric Eigenspace Representation', Proc. of 9th Scandinavian Conference on Image Analysis, 325–332, June 1995.
Nene S.A., Nayar S. and Murase H., 'sLAM: Software Library for Appearance Matching,’ Proc. of ARPA Image Understanding Workshop, Monterey, November 1994.
Pentland A., Moghaddam B. and Starner T., ‘View-based and modular eigenspaces for face recognition', Proc CVPR, 84–91, 1994.
Pillow N., Utcke S. and Zisserman A., ‘Viewpoint-Invariant Representation of Generalized Cylinders Using the Symmetry Set'. Image and Vision Computing, 13, 5, 1995.
Rothwell C.A. Object Recognition through Invariant Indexing., OUP, 1995.
Zisserman A., Forsyth D., Mundy J., Rothwell C., Liu J. and Pillow N., ‘3D Object Recognition using Invariance', AI Journal, 78, 239–288, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mundy, J. et al. (1996). An experimental comparison of appearance and geometric model based recognition. In: Ponce, J., Zisserman, A., Hebert, M. (eds) Object Representation in Computer Vision II. ORCV 1996. Lecture Notes in Computer Science, vol 1144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61750-7_32
Download citation
DOI: https://doi.org/10.1007/3-540-61750-7_32
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61750-1
Online ISBN: 978-3-540-70673-1
eBook Packages: Springer Book Archive