On the Evolution of Interest Operators using Genetic
Programming
M. Ebner. Late Breaking Papers at EuroGP'98: the First European
Workshop on Genetic Programming, page 6--10. Paris, France, CSRP-98-10, The University of Birmingham, UK, (14-15 April 1998)
Abstract
Interest operators play an important role in computer
vision. Depending on the type of the environment some
features may prove to be more advantageous than others.
Thus detection of interesting features has to be made
adaptive such that the best features according to some
measure are extracted. We are trying to evolve such
feature detectors using genetic programming. In this
paper we describe our results where the desired
operator, which is a Moravec interest operator, is
directly specified. We show that the problem is a
rather difficult one. Only an approximation to the
Moravec operator could be evolved using several sets of
elementary functions. 1 Motivation Interest operators
play an important role in computer vision 8. They
highlight points which can be found easily using simple
correlation methods. They can be used to calculate
accurate distance information and for map building
23. However no interest operator is suitable for all
types of environments. A mobile robot which ma...
%0 Conference Paper
%1 ebner:1998:eioGP
%A Ebner, Marc
%B Late Breaking Papers at EuroGP'98: the First European
Workshop on Genetic Programming
%C Paris, France
%D 1998
%E Poli, Riccardo
%E Langdon, W. B.
%E Schoenauer, Marc
%E Fogarty, Terry
%E Banzhaf, Wolfgang
%I CSRP-98-10, The University of Birmingham, UK
%K algorithms, genetic programming
%P 6--10
%T On the Evolution of Interest Operators using Genetic
Programming
%U http://citeseer.ist.psu.edu/158450.html
%X Interest operators play an important role in computer
vision. Depending on the type of the environment some
features may prove to be more advantageous than others.
Thus detection of interesting features has to be made
adaptive such that the best features according to some
measure are extracted. We are trying to evolve such
feature detectors using genetic programming. In this
paper we describe our results where the desired
operator, which is a Moravec interest operator, is
directly specified. We show that the problem is a
rather difficult one. Only an approximation to the
Moravec operator could be evolved using several sets of
elementary functions. 1 Motivation Interest operators
play an important role in computer vision 8. They
highlight points which can be found easily using simple
correlation methods. They can be used to calculate
accurate distance information and for map building
23. However no interest operator is suitable for all
types of environments. A mobile robot which ma...
@inproceedings{ebner:1998:eioGP,
abstract = {Interest operators play an important role in computer
vision. Depending on the type of the environment some
features may prove to be more advantageous than others.
Thus detection of interesting features has to be made
adaptive such that the best features according to some
measure are extracted. We are trying to evolve such
feature detectors using genetic programming. In this
paper we describe our results where the desired
operator, which is a Moravec interest operator, is
directly specified. We show that the problem is a
rather difficult one. Only an approximation to the
Moravec operator could be evolved using several sets of
elementary functions. 1 Motivation Interest operators
play an important role in computer vision [8]. They
highlight points which can be found easily using simple
correlation methods. They can be used to calculate
accurate distance information and for map building
[23]. However no interest operator is suitable for all
types of environments. A mobile robot which ma...},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Paris, France},
author = {Ebner, Marc},
biburl = {https://www.bibsonomy.org/bibtex/238f7e2a3ee1d50c84111b962c14c0700/brazovayeye},
booktitle = {Late Breaking Papers at EuroGP'98: the First European
Workshop on Genetic Programming},
editor = {Poli, Riccardo and Langdon, W. B. and Schoenauer, Marc and Fogarty, Terry and Banzhaf, Wolfgang},
interhash = {8b50c4b00e472d4fe48c4e86da92884f},
intrahash = {38f7e2a3ee1d50c84111b962c14c0700},
keywords = {algorithms, genetic programming},
month = {14-15 April},
notes = {EuroGP'98LB part of \cite{Poli:1998:egplb}},
pages = {6--10},
publisher = {CSRP-98-10, The University of Birmingham, UK},
publisher_address = {School of Computer Science},
size = {5 pages},
timestamp = {2008-06-19T17:39:01.000+0200},
title = {On the Evolution of Interest Operators using Genetic
Programming},
url = {http://citeseer.ist.psu.edu/158450.html},
year = 1998
}