Invariant object recognition by shape space analysis
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 581-585
- https://doi.org/10.1109/icip.1998.999044
Abstract
This paper describes a new approach to invariant object recognition. In this approach, an object is represented by a set of key points called landmarks. All possible translation, scaling, and rotation of the object are placed into an equivalent class and associated to a single point in a complex projective space called the shape space. Object recognition is then achieved by distance calculations in this shape space. This approach is invariant to object translation, scaling, and rotation, and is computationally simple. Our experimental results also indicate that it is insensitive to noise and moderate occlusions.Keywords
This publication has 5 references indexed in Scilit:
- Partial shape recognition: a landmark-based approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Multiscale geometrical feature extraction and object recognition with wavelets and morphologyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Shape Manifolds, Procrustean Metrics, and Complex Projective SpacesBulletin of the London Mathematical Society, 1984
- Fourier Descriptors for Plane Closed CurvesIEEE Transactions on Computers, 1972
- Visual pattern recognition by moment invariantsIEEE Transactions on Information Theory, 1962