A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
Authors:
Open Access
- 1 January 2011
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Computational Neuroscience
- Vol. 5, 9938
Abstract
Visual object recognition occurs easily despite differences in position, size, and rotation of the object, but the neural mechanisms responsible for this invariance are not known. We have found a set of transforms that achieve invariance in a neurally plausible way. We find that a transform based on local spatial frequency analysis of oriented segments and on logarithmic mapping, when applied twice in an iterative fashion, produces an output image that is unique to the object and that remains constant as the input image is shifted, scaled or rotated.Keywords
This publication has 55 references indexed in Scilit:
- Serial, Covert Shifts of Attention during Visual Search Are Reflected by the Frontal Eye Fields and Correlated with Population OscillationsNeuron, 2009
- Faculty Opinions recommendation of A precise retinotopic map of primate striate cortex generated from the representation of angioscotomas.2003
- The minicolumn hypothesis in neuroscienceBrain, 2002
- Invariant recognition of feature combinations in the visual systemBiological Cybernetics, 2002
- The layout of iso-orientation domains in area 18 of cat visual cortex: optical imaging reveals a pinwheel-like organizationThe Journal of Neuroscience, 1993
- Spatial‐frequency‐specific inhibition in cat striate cortex cells.The Journal of Physiology, 1983
- Spatial frequency selectivity of cells in macaque visual cortexVision Research, 1982
- Monocular and binocular detection of moving sinusoidal gratingsVision Research, 1981
- Relationship between spatial frequency selectivity and receptive field profile of simple cells.The Journal of Physiology, 1979
- Position, rotation, and scale invariant optical correlationApplied Optics, 1976