Retinal sampling, feature detection and saccades; A statistical perspective.
Retinal sampling, feature detection and saccades; A statistical perspective.
This paper applies statistical design principles to a simple biological model of human vision so that we can more clearly interpret the apparent role of eye saccades. In doing so we show that many structural features of the biological system (such as the optical geometry of the retina) are strategies for minimising the resources required to construct a working image recognition system. The ideas presented have implications for the construction of arti-ficial (computer) vision systems. The computational model is very closely related to (but not based upon) SIFT, but more strongly based on a consideration of vision as a process of measurment while also linking the idea of multi-scale analysis with biological structure.
Thacker, N. A.
9758be5f-c9fa-455f-815c-34d8629230df
Leek, E. C.
6f63c405-e28f-4f8c-8ead-3b0a79c7dc88
2007
Thacker, N. A.
9758be5f-c9fa-455f-815c-34d8629230df
Leek, E. C.
6f63c405-e28f-4f8c-8ead-3b0a79c7dc88
Thacker, N. A. and Leek, E. C.
(2007)
Retinal sampling, feature detection and saccades; A statistical perspective.
2007 18th British Machine Vision Conference, BMVC 2007, , Warwick, United Kingdom.
10 - 13 Sep 2007.
10 pp
.
(doi:10.5244/C.21.101).
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper applies statistical design principles to a simple biological model of human vision so that we can more clearly interpret the apparent role of eye saccades. In doing so we show that many structural features of the biological system (such as the optical geometry of the retina) are strategies for minimising the resources required to construct a working image recognition system. The ideas presented have implications for the construction of arti-ficial (computer) vision systems. The computational model is very closely related to (but not based upon) SIFT, but more strongly based on a consideration of vision as a process of measurment while also linking the idea of multi-scale analysis with biological structure.
This record has no associated files available for download.
More information
Published date: 2007
Venue - Dates:
2007 18th British Machine Vision Conference, BMVC 2007, , Warwick, United Kingdom, 2007-09-10 - 2007-09-13
Identifiers
Local EPrints ID: 494701
URI: http://eprints.soton.ac.uk/id/eprint/494701
PURE UUID: ef67c4a6-4a28-4a42-bfb8-14af23c0e3c0
Catalogue record
Date deposited: 14 Oct 2024 16:42
Last modified: 15 Oct 2024 02:10
Export record
Altmetrics
Contributors
Author:
N. A. Thacker
Author:
E. C. Leek
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics