In this paper, a novel genetically-inspired visual learning method is proposed. Given the training images, this general approach induces a sophisticated feature-based recognition system, by using cooperative coevolution and linear genetic programming for the procedural representation of feature extraction agents. The paper describes the learning algorithm and provides a firm rationale for its design. An extensive experimental evaluation, on the demanding real-world task of object recognition in synthetic aperture radar (SAR) imagery, shows the competitiveness of the proposed approach with human-designed recognition systems.
@INPROCEEDINGS { KrawiecBhanu03a,
ABSTRACT = { In this paper, a novel genetically-inspired visual learning method is proposed. Given the training images, this general approach induces a sophisticated feature-based recognition system, by using cooperative coevolution and linear genetic programming for the procedural representation of feature extraction agents. The paper describes the learning algorithm and provides a firm rationale for its design. An extensive experimental evaluation, on the demanding real-world task of object recognition in synthetic aperture radar (SAR) imagery, shows the competitiveness of the proposed approach with human-designed recognition systems. },
ADDRESS = { Chicago, {IL}, July 12-16 },
AUTHOR = { K. Krawiec and B. Bhanu },
BOOKTITLE = { Genetic and Evolutionary Computation },
EDITOR = { E. Cant{\'u}-Paz and and others },
PAGES = { 332--343 },
PUBLISHER = { Springer-Verlag },
SERIES = { Lecture Notes in Computer Science },
TITLE = { Coevolution and Linear Genetic Programming for Visual Learning },
VOLUME = { 2723 },
YEAR = { 2003 },
}