creators_name: Würtz, R.P.
creators_name: Lourens, T.
editors_name: Germond, A.
editors_name: Hasler, M.
editors_name: Nicoud, J.
type: confpaper
datestamp: 1998-07-31
lastmod: 2011-03-11 08:54:00
metadata_visibility: show
title: Corner detection in color images by multiscale combination of end-stopped cortical cells.
ispublished: pub
subjects: bio-ani-cog
subjects: comp-neuro-sci
subjects: comp-sci-art-intel
subjects: comp-sci-mach-vis
subjects: neuro-mod
full_text_status: public
keywords: corner detection, end-stopped cells, color image, multiscale methods
abstract: We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex. Shortcomings of this model are overcome by a combination over several scales. The notion of an end-stopped cell and the resulting corner detector is generalized to color channels in a biologically plausible way. The resulting corner detection method yields good results in the presence of high frequency texture, noise, varying contrast, and rounded corners. This compares favorably with known corner detectors.
date: 1997
date_type: published
publisher: Springer
pagerange: 901-906
refereed: FALSE
citation:   Würtz, R.P. and Lourens, T.  (1997) Corner detection in color images by multiscale combination of end-stopped cortical cells.  [Conference Paper]     
document_url: http://cogprints.org/504/2/rolf-icann97.ps