In this paper, a novel genetically inspired visual learning method is proposed. Given the training raster images, this general approach induces a sophisticated feature-based recognition system. It employs the paradigm of cooperative coevolution to handle the computational difficulty of this task. To represent the feature extraction agents, the linear genetic programming is used. The paper describes the learning algorithm and provides a firm rationale for its design. Different architectures of recognition systems are considered that employ the proposed feature synthesis method. An extensive experimental evaluation on the demanding real-world task of object recognition in synthetic aperture radar (SAR) imagery shows the ability of the proposed approach to attain high recognition performance in different operating conditions.
@ARTICLE { KrawiecBhanu05,
ABSTRACT = { In this paper, a novel genetically inspired visual learning method is proposed. Given the training raster images, this general approach induces a sophisticated feature-based recognition system. It employs the paradigm of cooperative coevolution to handle the computational difficulty of this task. To represent the feature extraction agents, the linear genetic programming is used. The paper describes the learning algorithm and provides a firm rationale for its design. Different architectures of recognition systems are considered that employ the proposed feature synthesis method. An extensive experimental evaluation on the demanding real-world task of object recognition in synthetic aperture radar (SAR) imagery shows the ability of the proposed approach to attain high recognition performance in different operating conditions. },
AUTHOR = { Krzysztof Krawiec and Bir Bhanu },
JOURNAL = { {IEEE} Transactions on System, Man, and Cybernetics -- Part B },
MONTH = { June },
NUMBER = { 3 },
PAGES = { 409--425 },
TITLE = { Visual Learning by Coevolutionary Feature Synthesis },
URL = { http://ieeexplore.ieee.org/iel5/3477/30862/01430827.pdf },
VOLUME = { 35 },
YEAR = { 2005 },
1 = { http://ieeexplore.ieee.org/iel5/3477/30862/01430827.pdf },
}