Genetic Programming for Image Recognition: An LGP
Approach
M. Zhang, and C. Fogelberg. Applications of Evolutionary Computing,
EvoWorkshops2007: EvoCOMNET, EvoFIN, EvoIASP,
EvoInteraction, EvoMUSART, EvoSTOC,
EvoTransLog, volume 4448 of LNCS, page 340--350. Valencia, Spain, Springer Verlag, (11-13 April 2007)
DOI: doi:10.1007/978-3-540-71805-5_37
Abstract
This paper describes a linear genetic programming
approach to multi-class image recognition problems. A
new fitness function is introduced to approximate the
true feature space. The results show that this approach
outperforms the basic tree based genetic programming
approach on all the tasks investigated here and that
the programs evolved by this approach are easier to
interpret. The investigation on the extra registers and
program length results in heuristic guidelines for
initially setting system parameters.
%0 Conference Paper
%1 zhang:evows07
%A Zhang, Mengjie
%A Fogelberg, Christopher Graeme
%B Applications of Evolutionary Computing,
EvoWorkshops2007: EvoCOMNET, EvoFIN, EvoIASP,
EvoInteraction, EvoMUSART, EvoSTOC,
EvoTransLog
%C Valencia, Spain
%D 2007
%E Giacobini, Mario
%E Brabazon, Anthony
%E Cagnoni, Stefano
%E Di Caro, Gianni A.
%E Drechsler, Rolf
%E Farooq, Muddassar
%E Fink, Andreas
%E Lutton, Evelyne
%E Machado, Penousal
%E Minner, Stefan
%E O'Neill, Michael
%E Romero, Juan
%E Rothlauf, Franz
%E Squillero, Giovanni
%E Takagi, Hideyuki
%E Uyar, A. Sima
%E Yang, Shengxiang
%I Springer Verlag
%K algorithms, genetic programming
%P 340--350
%R doi:10.1007/978-3-540-71805-5_37
%T Genetic Programming for Image Recognition: An LGP
Approach
%V 4448
%X This paper describes a linear genetic programming
approach to multi-class image recognition problems. A
new fitness function is introduced to approximate the
true feature space. The results show that this approach
outperforms the basic tree based genetic programming
approach on all the tasks investigated here and that
the programs evolved by this approach are easier to
interpret. The investigation on the extra registers and
program length results in heuristic guidelines for
initially setting system parameters.
@inproceedings{zhang:evows07,
abstract = {This paper describes a linear genetic programming
approach to multi-class image recognition problems. A
new fitness function is introduced to approximate the
true feature space. The results show that this approach
outperforms the basic tree based genetic programming
approach on all the tasks investigated here and that
the programs evolved by this approach are easier to
interpret. The investigation on the extra registers and
program length results in heuristic guidelines for
initially setting system parameters.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Valencia, Spain},
author = {Zhang, Mengjie and Fogelberg, Christopher Graeme},
biburl = {https://www.bibsonomy.org/bibtex/2d76cdab6c34d49265228eb387e420e5f/brazovayeye},
booktitle = {Applications of Evolutionary Computing,
EvoWorkshops2007: {EvoCOMNET}, {EvoFIN}, {EvoIASP},
{EvoInteraction}, {EvoMUSART}, {EvoSTOC},
{EvoTransLog}},
doi = {doi:10.1007/978-3-540-71805-5_37},
editor = {Giacobini, Mario and Brabazon, Anthony and Cagnoni, Stefano and {Di Caro}, Gianni A. and Drechsler, Rolf and Farooq, Muddassar and Fink, Andreas and Lutton, Evelyne and Machado, Penousal and Minner, Stefan and O'Neill, Michael and Romero, Juan and Rothlauf, Franz and Squillero, Giovanni and Takagi, Hideyuki and Uyar, A. Sima and Yang, Shengxiang},
interhash = {d82d77eafeb4e79892888454750f50be},
intrahash = {d76cdab6c34d49265228eb387e420e5f},
isbn13 = {978-3-540-71804-8},
keywords = {algorithms, genetic programming},
month = {11-13 April},
notes = {EvoWorkshops2007},
pages = {340--350},
publisher = {Springer Verlag},
series = {LNCS},
timestamp = {2008-06-19T17:55:45.000+0200},
title = {Genetic Programming for Image Recognition: An {LGP}
Approach},
volume = 4448,
year = 2007
}