Object class recognition is a highly challenging area in computer
vision and machine learning. In this paper, we introduce a novel
approach to object class recognition using Neuro Evolution of Augmenting
Topologies (NEAT) to evolve artificial neural networks (ANN) capable
of taking advantage of the robust SIFT feature based descriptor histograms.
We claim that NEAT can produce ANN classifier which exhibits outstanding
ability of learning from only afew training examples without sacrificing
accuracy. Our empirical evaluations against the performance of state
of the art statistical machine learning method such as support vector
machine show that NEAT-evolved ANN classifier outperforms by an average
of 9.96% higher accuracy when presented with very small training
set proving its superior ability to generalize its learning.
%0 Journal Article
%1 AbulHasanat2008
%A Hasanat, M.H. Abul
%A Harun, S.Z.
%A Ramachandram, D.
%A Rajeswari, M.
%D 2008
%J Computer Graphics, Imaging and Visualisation, 2008. CGIV '08. Fifth
International Conference on
%K (artificial ANN Augmenting Evolution NEAT-evolved Neuro SIFT Topologies, art artificial class classifier, computer descriptor feature, histograms, intelligence), learning learning, machine nets, network, neural object of recognition, recognitionNEAT-evolved robust statistical support vector vision,
%P 271-275
%R 10.1109/CGIV.2008.35
%T Object Class Recognition Using NEAT-Evolved Artificial Neural Network
%X Object class recognition is a highly challenging area in computer
vision and machine learning. In this paper, we introduce a novel
approach to object class recognition using Neuro Evolution of Augmenting
Topologies (NEAT) to evolve artificial neural networks (ANN) capable
of taking advantage of the robust SIFT feature based descriptor histograms.
We claim that NEAT can produce ANN classifier which exhibits outstanding
ability of learning from only afew training examples without sacrificing
accuracy. Our empirical evaluations against the performance of state
of the art statistical machine learning method such as support vector
machine show that NEAT-evolved ANN classifier outperforms by an average
of 9.96% higher accuracy when presented with very small training
set proving its superior ability to generalize its learning.
@article{AbulHasanat2008,
abstract = {Object class recognition is a highly challenging area in computer
vision and machine learning. In this paper, we introduce a novel
approach to object class recognition using Neuro Evolution of Augmenting
Topologies (NEAT) to evolve artificial neural networks (ANN) capable
of taking advantage of the robust SIFT feature based descriptor histograms.
We claim that NEAT can produce ANN classifier which exhibits outstanding
ability of learning from only afew training examples without sacrificing
accuracy. Our empirical evaluations against the performance of state
of the art statistical machine learning method such as support vector
machine show that NEAT-evolved ANN classifier outperforms by an average
of 9.96% higher accuracy when presented with very small training
set proving its superior ability to generalize its learning.},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Hasanat, M.H. Abul and Harun, S.Z. and Ramachandram, D. and Rajeswari, M.},
biburl = {https://www.bibsonomy.org/bibtex/22e9785bc1cd0be637a8eba1ad7a7aca1/mozaher},
doi = {10.1109/CGIV.2008.35},
file = {:AbulHasanat2008.pdf:PDF},
interhash = {6e99151eb7d8133d9f5a724e34e365a1},
intrahash = {2e9785bc1cd0be637a8eba1ad7a7aca1},
journal = {Computer Graphics, Imaging and Visualisation, 2008. CGIV '08. Fifth
International Conference on},
keywords = {(artificial ANN Augmenting Evolution NEAT-evolved Neuro SIFT Topologies, art artificial class classifier, computer descriptor feature, histograms, intelligence), learning learning, machine nets, network, neural object of recognition, recognitionNEAT-evolved robust statistical support vector vision,},
month = {Aug.},
owner = {Mozaherul Hoque},
pages = {271-275},
timestamp = {2009-09-12T19:19:35.000+0200},
title = {Object Class Recognition Using NEAT-Evolved Artificial Neural Network},
year = 2008
}