Front-end vision: A multiscale geometry engine

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

12 Citations (Scopus)
8 Downloads (Pure)


The paper is a short tutorial on the multiscale differential geometric possibilities of the front-end visual receptive fields, modeled by Gaussian derivative kernels. The paper is written in, and interactive through the use of Mathematica 4, so each statement can be run and modified by the reader on images of choice. The notion of multiscale invariant feature detection is presented in detail, with examples of second, third and fourth order of differentiation.
Original languageEnglish
Title of host publicationBiologically motivated computer vision. Proceedings of the First IEEE International Workshop, BMCV 2000 Seoul, Korea, May 15–17, 2000
EditorsS.-W. Lee, H.H. Bulthoff, T. Poggio
Place of PublicationBerlin
Number of pages11
ISBN (Print)978-3-540-67560-0
Publication statusPublished - 2000
EventFirst IEEE International Workshop, BMCV 2000 Seoul, Korea - Seoul, Korea, Democratic People's Republic of
Duration: 15 May 200017 May 2000

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


ConferenceFirst IEEE International Workshop, BMCV 2000 Seoul, Korea
Country/TerritoryKorea, Democratic People's Republic of


Dive into the research topics of 'Front-end vision: A multiscale geometry engine'. Together they form a unique fingerprint.

Cite this