Recognition by linear combinations of models
- 1 January 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13 (10) , 992-1006
- https://doi.org/10.1109/34.99234
Abstract
An approach to visual object recognition in which a 3D object is represented by the linear combination of 2D images of the object is proposed. It is shown that for objects with sharp edges as well as with smooth bounding contours, the set of possible images of a given object is embedded in a linear space spanned by a small number of views. For objects with sharp edges, the linear combination representation is exact. For objects with smooth boundaries, it is an approximation that often holds over a wide range of viewing angles. Rigid transformations (with or without scaling) can be distinguished from more general linear transformations of the object by testing certain constraints placed on the coefficients of the linear combinations. Three alternative methods of determining the transformation that matches a model to a given image are proposed.Keywords
This publication has 18 references indexed in Scilit:
- The combinatorics of heuristic search termination for object recognition in cluttered environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Aligning pictorial descriptions: An approach to object recognitionCognition, 1989
- Motion and structure from orthographic projectionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Optical Neural ComputersScientific American, 1987
- The Representation, Recognition, and Locating of 3-D ObjectsThe International Journal of Robotics Research, 1986
- Human image understanding: Recent research and a theoryComputer Vision, Graphics, and Image Processing, 1985
- Model-Based Recognition and Localization from Sparse Range or Tactile DataThe International Journal of Robotics Research, 1984
- A computer algorithm for reconstructing a scene from two projectionsNature, 1981
- Random sample consensusCommunications of the ACM, 1981
- Directional selectivity and its use in early visual processingProceedings of the Royal Society of London. B. Biological Sciences, 1981