M. Johnson, P. Maes, and T. Darrell. ARTIFICIAL LIFE IV, Proceedings of the fourth
International Workshop on the Synthesis and Simulation
of Living Systems, page 198--209. MIT, Cambridge, MA, USA, MIT Press, (6-8 July 1994)
Abstract
Traditional machine vision assumes that the vision
system recovers a complete, labeled description of the
world Marr. Recently, several researchers have
criticized this model and proposed an alternative model
which considers perception as a distributed collection
of task-specific, task-driven visual routines
Aloimonos, Ullman. Some of these researchers have
argued that in natural living systems these visual
routines are the product of natural selection
ramachandran. So far, researchers have hand-coded
task-specific visual routines for actual
implementations (e.g. Chapman). In this paper we
propose an alternative approach in which visual
routines for simple tasks are evolved using an
artificial evolution approach. We present results from
a series of runs on actual camera images, in which
simple routines were evolved using Genetic Programming
techniques Koza. The results obtained are promising:
the evolved routines are able to correctly classify up
to 93% of the images, which is better than the best
algorithm we were able to write by hand.
%0 Conference Paper
%1 johnson:1994:EVR
%A Johnson, Michael Patrick
%A Maes, Pattie
%A Darrell, Trevor
%B ARTIFICIAL LIFE IV, Proceedings of the fourth
International Workshop on the Synthesis and Simulation
of Living Systems
%C MIT, Cambridge, MA, USA
%D 1994
%E Brooks, Rodney A.
%E Maes, Pattie
%I MIT Press
%K algorithms, genetic programming
%P 198--209
%T Evolving Visual Routines
%U http://citeseer.ist.psu.edu/402594.html
%X Traditional machine vision assumes that the vision
system recovers a complete, labeled description of the
world Marr. Recently, several researchers have
criticized this model and proposed an alternative model
which considers perception as a distributed collection
of task-specific, task-driven visual routines
Aloimonos, Ullman. Some of these researchers have
argued that in natural living systems these visual
routines are the product of natural selection
ramachandran. So far, researchers have hand-coded
task-specific visual routines for actual
implementations (e.g. Chapman). In this paper we
propose an alternative approach in which visual
routines for simple tasks are evolved using an
artificial evolution approach. We present results from
a series of runs on actual camera images, in which
simple routines were evolved using Genetic Programming
techniques Koza. The results obtained are promising:
the evolved routines are able to correctly classify up
to 93% of the images, which is better than the best
algorithm we were able to write by hand.
@inproceedings{johnson:1994:EVR,
abstract = {Traditional machine vision assumes that the vision
system recovers a complete, labeled description of the
world [Marr]. Recently, several researchers have
criticized this model and proposed an alternative model
which considers perception as a distributed collection
of task-specific, task-driven visual routines
[Aloimonos, Ullman]. Some of these researchers have
argued that in natural living systems these visual
routines are the product of natural selection
[ramachandran]. So far, researchers have hand-coded
task-specific visual routines for actual
implementations (e.g. [Chapman]). In this paper we
propose an alternative approach in which visual
routines for simple tasks are evolved using an
artificial evolution approach. We present results from
a series of runs on actual camera images, in which
simple routines were evolved using Genetic Programming
techniques [Koza]. The results obtained are promising:
the evolved routines are able to correctly classify up
to 93% of the images, which is better than the best
algorithm we were able to write by hand.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {MIT, Cambridge, MA, USA},
author = {Johnson, Michael Patrick and Maes, Pattie and Darrell, Trevor},
biburl = {https://www.bibsonomy.org/bibtex/2d6cfb6dee1ac4ef65c70bee3079df4e2/brazovayeye},
booktitle = {ARTIFICIAL LIFE IV, Proceedings of the fourth
International Workshop on the Synthesis and Simulation
of Living Systems},
editor = {Brooks, Rodney A. and Maes, Pattie},
interhash = {796f1792a8517c3313186869cedd5d02},
intrahash = {d6cfb6dee1ac4ef65c70bee3079df4e2},
keywords = {algorithms, genetic programming},
month = {6-8 July},
notes = {alife-4
See also \cite{johnson:1994:EVRAL}},
pages = {198--209},
publisher = {MIT Press},
timestamp = {2008-06-19T17:42:30.000+0200},
title = {Evolving Visual Routines},
url = {http://citeseer.ist.psu.edu/402594.html},
year = 1994
}