The canonical coordinates method for pattern deformation: theoretical and computational considerations
- 1 January 1992
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 14 (12), 1171-1183
- https://doi.org/10.1109/34.177382
Abstract
A method for the analysis of deformed patterns is presented and analyzed. The image is transformed into a new set of coordinates in which the deformation has a particular simple form. A number of deformations are considered. The practical implementation of the method is discussed. We also consider similar aspects of biological vision.Keywords
This publication has 21 references indexed in Scilit:
- The finite Zak transform: An efficient tool for image representation and analysisJournal of Visual Communication and Image Representation, 1992
- The generalized Gabor scheme of image representation in biological and machine visionIeee Transactions On Pattern Analysis and Machine Intelligence, 1988
- Complete discrete 2-D Gabor transforms by neural networks for image analysis and compressionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Relationship between integral transform invariances and Lie group theoryJournal of the Optical Society of America A, 1988
- Exploration of the primary visual cortex, 1955–78Nature, 1982
- Directional selectivity and its use in early visual processingProceedings of the Royal Society of London. B. Biological Sciences, 1981
- Subjective geometry and geometric psychologyMathematical Modelling, 1980
- Computational anatomy and functional architecture of striate cortex: A spatial mapping approach to perceptual codingVision Research, 1980
- Subjective Lorentz transformations and the perception of motion*Journal of the Optical Society of America, 1978
- Scale invariant optical correlation using Mellin transformsOptics Communications, 1976