A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Sountsov, Pavel, Santucci, David M., Lisman, John E.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Research Foundation 2011
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3222220/
https://www.ncbi.nlm.nih.gov/pubmed/22125522
http://dx.doi.org/10.3389/fncom.2011.00053
_version_ 1782217186350202880
author Sountsov, Pavel
Santucci, David M.
Lisman, John E.
author_facet Sountsov, Pavel
Santucci, David M.
Lisman, John E.
author_sort Sountsov, Pavel
collection PubMed
description 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.
format Online
Article
Text
id pubmed-3222220
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher Frontiers Research Foundation
record_format MEDLINE/PubMed
spelling pubmed-32222202011-11-28 A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation Sountsov, Pavel Santucci, David M. Lisman, John E. Front Comput Neurosci Neuroscience 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. Frontiers Research Foundation 2011-11-22 /pmc/articles/PMC3222220/ /pubmed/22125522 http://dx.doi.org/10.3389/fncom.2011.00053 Text en Copyright © 2011 Sountsov, Santucci and Lisman. http://www.frontiersin.org/licenseagreement This is an open-access article subject to a non-exclusive license between the authors and Frontiers Media SA, which permits use, distribution and reproduction in other forums, provided the original authors and source are credited and other Frontiers conditions are complied with.
spellingShingle Neuroscience
Sountsov, Pavel
Santucci, David M.
Lisman, John E.
A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
title A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
title_full A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
title_fullStr A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
title_full_unstemmed A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
title_short A Biologically Plausible Transform for Visual Recognition that is Invariant to Translation, Scale, and Rotation
title_sort biologically plausible transform for visual recognition that is invariant to translation, scale, and rotation
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3222220/
https://www.ncbi.nlm.nih.gov/pubmed/22125522
http://dx.doi.org/10.3389/fncom.2011.00053
work_keys_str_mv AT sountsovpavel abiologicallyplausibletransformforvisualrecognitionthatisinvarianttotranslationscaleandrotation
AT santuccidavidm abiologicallyplausibletransformforvisualrecognitionthatisinvarianttotranslationscaleandrotation
AT lismanjohne abiologicallyplausibletransformforvisualrecognitionthatisinvarianttotranslationscaleandrotation
AT sountsovpavel biologicallyplausibletransformforvisualrecognitionthatisinvarianttotranslationscaleandrotation
AT santuccidavidm biologicallyplausibletransformforvisualrecognitionthatisinvarianttotranslationscaleandrotation
AT lismanjohne biologicallyplausibletransformforvisualrecognitionthatisinvarianttotranslationscaleandrotation

Ejemplares similares