In this paper, we present a novel method for learning complex concepts/hypotheses directly from raw training data. The task addressed here concerns data-driven synthesis of recognition procedures for real-world object recognition task. The method uses linear genetic programming to encode potential solutions expressed in terms of elementary operations, and handles the complexity of the learning task by applying cooperative coevolution to decompose the problem automatically. The training consists in coevolving feature extraction procedures, each being a sequence of elementary image processing and feature extraction operations. Extensive experimental results show that the approach attains competitive performance for 3-D object recognition in real synthetic aperture radar (SAR) imagery.
@INPROCEEDINGS { KrawiecBhanu03,
ABSTRACT = { In this paper, we present a novel method for learning complex concepts/hypotheses directly from raw training data. The task addressed here concerns data-driven synthesis of recognition procedures for real-world object recognition task. The method uses linear genetic programming to encode potential solutions expressed in terms of elementary operations, and handles the complexity of the learning task by applying cooperative coevolution to decompose the problem automatically. The training consists in coevolving feature extraction procedures, each being a sequence of elementary image processing and feature extraction operations. Extensive experimental results show that the approach attains competitive performance for 3-D object recognition in real synthetic aperture radar (SAR) imagery. },
ADDRESS = { Menlo Park, CA },
AUTHOR = { K. Krawiec and B. Bhanu },
BOOKTITLE = { Proceedings of the Twentieth International Conference on Machine Learning ({ICML} 2003) },
EDITOR = { T. Fawcett and N. Mishra },
PAGES = { 376--383 },
PUBLISHER = { {AAAI} Press },
TITLE = { Visual Learning by Evolutionary Feature Synthesis },
YEAR = { 2003 },
}