a biologically plausible transform for visual recognition that is invariant to translation, scale and rotation
Clicks: 162
ID: 161183
2011
Article Quality & Performance Metrics
Overall Quality
Improving Quality
0.0
/100
Combines engagement data with AI-assessed academic quality
Reader Engagement
Emerging Content
4.2
/100
14 views
14 readers
Trending
AI Quality Assessment
Not analyzed
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.
| Reference Key |
esountsov2011frontiersa
Use this key to autocite in the manuscript while using
SciMatic Manuscript Manager or Thesis Manager
|
|---|---|
| Authors | ;Pavel eSountsov;David M Santucci;John E Lisman |
| Journal | population health management |
| Year | 2011 |
| DOI |
10.3389/fncom.2011.00053
|
| URL | |
| Keywords |
Citations
No citations found. To add a citation, contact the admin at info@scimatic.org
Comments
No comments yet. Be the first to comment on this article.