Efficient model library access by projectively invariant indexing functions
- 2 January 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 109-114
- https://doi.org/10.1109/cvpr.1992.223219
Abstract
Projectively invariant shape descriptors allow fastindexing into model libraries without the need for posecomputation or camera calibration. This paper describesprogress in building a model based vision systemfor plane objects that uses algebraic projective invariants.We give a brief account of these descriptors andthen describe the recognition system, giving examplesof the invariant techniques working on real images.1 Introduction.A major unsolved problem in model-based visionis the ...Keywords
This publication has 13 references indexed in Scilit:
- Model group indexing for recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Efficiently using invariant theory for model-based matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Fast affine point matching: an output-sensitive methodPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The evolution and testing of a model-based object recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Canonical frames for planar object recognitionPublished by Springer Nature ,1992
- Invariant descriptors for 3D object recognition and posePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Projective area-invariants as an extension of the cross-ratioCVGIP: Image Understanding, 1991
- Localizing Overlapping Parts by Searching the Interpretation TreePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- The viewpoint consistency constraintInternational Journal of Computer Vision, 1987
- A Computational Approach to Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986