Shape description from imperfect and incomplete data
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 125-129 vol.1
- https://doi.org/10.1109/icpr.1990.118077
Abstract
Usually, shape description systems assume that a scene has been segmented into objects and that object boundaries are given. This, however, is not realistic when working with intensity images; the resulting boundaries are fragmented and contain surface markings, and shadow and noise boundaries. A system is described which works with such input and computes shape descriptions of complex objects. Scene segmentation takes place through shape description. Generalized cones or, more precisely, their 2D analogs of ribbons are used as the basic shape representation scheme. Results for synthetic and real examples are shown. The output of the system is useful for object recognition, learning, further inference of 3D shape, grasping, and navigation.Keywords
This publication has 8 references indexed in Scilit:
- Using Symmetries For Analysis Of Shape From ContourPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Specifying heterogeneous suites for vision tasksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Computing volume descriptions from sparse 3-D dataInternational Journal of Computer Vision, 1988
- A Computational Approach to Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Smoothed Local Symmetries and Their ImplementationThe International Journal of Robotics Research, 1984
- Analysis of occluding contourProceedings of the Royal Society of London. B. Biological Sciences, 1977
- Description and recognition of curved objects☆Artificial Intelligence, 1977
- Biological shape and visual science (part I)Journal of Theoretical Biology, 1973