New Fitness Functions in Genetic Programming for
Object Detection
M. Lett, and M. Zhang. Proceeding of Image and Vision Computing International
Conference, page 441--446. Akaroa, New Zealand, Lincoln, Landcare Research, (November 2004)
Abstract
Object detection is an important field of research in
computer vision which genetic programming has been
applied to recently. This paper describes two new
fitness functions in genetic programming for object
detection. Both fitness functions are based on recall
and precision of genetic programs. The first is a
tolerance based fitness function and the second is a
weighted fitness function. The merits and effectiveness
of the two fitness function are discussed. The two
fitness functions are examined and compared on three
object detection problems of increasing dificulty. The
results suggest that both fitness functions perform
very well on the relatively easy problem, the weighted
fitness function outperforms the tolerance based
fitness function on the relatively dificult problems.
%0 Conference Paper
%1 LettZhang:04:ivcnz
%A Lett, Malcolm
%A Zhang, Mengjie
%B Proceeding of Image and Vision Computing International
Conference
%C Akaroa, New Zealand
%D 2004
%E Pairman, David
%E North, Heather
%E McNeill, Stephen
%I Lincoln, Landcare Research
%K algorithms, detection, fitness function genetic localisation, object programming,
%P 441--446
%T New Fitness Functions in Genetic Programming for
Object Detection
%X Object detection is an important field of research in
computer vision which genetic programming has been
applied to recently. This paper describes two new
fitness functions in genetic programming for object
detection. Both fitness functions are based on recall
and precision of genetic programs. The first is a
tolerance based fitness function and the second is a
weighted fitness function. The merits and effectiveness
of the two fitness function are discussed. The two
fitness functions are examined and compared on three
object detection problems of increasing dificulty. The
results suggest that both fitness functions perform
very well on the relatively easy problem, the weighted
fitness function outperforms the tolerance based
fitness function on the relatively dificult problems.
@inproceedings{LettZhang:04:ivcnz,
abstract = {Object detection is an important field of research in
computer vision which genetic programming has been
applied to recently. This paper describes two new
fitness functions in genetic programming for object
detection. Both fitness functions are based on recall
and precision of genetic programs. The first is a
tolerance based fitness function and the second is a
weighted fitness function. The merits and effectiveness
of the two fitness function are discussed. The two
fitness functions are examined and compared on three
object detection problems of increasing dificulty. The
results suggest that both fitness functions perform
very well on the relatively easy problem, the weighted
fitness function outperforms the tolerance based
fitness function on the relatively dificult problems.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Akaroa, New Zealand},
author = {Lett, Malcolm and Zhang, Mengjie},
biburl = {https://www.bibsonomy.org/bibtex/23e38685fd4176b5f6f7e35a1d02cc6d7/brazovayeye},
booktitle = {Proceeding of Image and Vision Computing International
Conference},
editor = {Pairman, David and North, Heather and McNeill, Stephen},
interhash = {a0ac0e9bc448d1c41039ef8cd39a0511},
intrahash = {3e38685fd4176b5f6f7e35a1d02cc6d7},
keywords = {algorithms, detection, fitness function genetic localisation, object programming,},
month = {November},
notes = {Fri, 02 Jun 2006 17:03:20 +0800 IVCNZ},
pages = {441--446},
publisher = {Lincoln, Landcare Research},
size = {6 pages},
timestamp = {2008-06-19T17:45:25.000+0200},
title = {New Fitness Functions in Genetic Programming for
Object Detection},
year = 2004
}