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.
On a temporary leave from Institute of Computing Science, Poznań University of Technology, Poznań Poland.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Banzhaf, W., Nordic, P., Keller, R., Francine, F.: Genetic Programming. An Introduction. On the automatic Evolution of Computer Programs and its Application. Morgan Kaufmann, San Francisco, Calif. (1998)
Bhanu, B., Jones, G.: Increasing the discrimination of SAR recognition models. Optical Engineering 12 (2002) 3298–3306
Bhanu, B. and Krawiec, K.: Coevolutionary construction of features for transformation of representation in machine learning. Proc. Genetic and Evolutionary Computation Conference (GECCO 2002). AAAI Press, New York (2002) 249–254
Breiman, L.: Bagging predictors. Machine Learning 24 (1996) 123–140
Draper, B., Hanson, A., Riseman, E.: Knowledge-Directed Vision: Control, Learning and Integration. Proc. IEEE 84 (1996) 1625–1637
Krawiec, K.: On the Use of Pair wise Comparison of Hypotheses in Evolutionary Learning Applied to Learning from Visual Examples. In: Perner, P. (ed.): Machine Learning and Data Mining in Pattern Recognition. Lecture Notes in Artificial Intelligence, Vol. 2123. Springer Verlag, Berlin (2001) 307–321.
Luke, S.: ECJ Evolutionary Computation System. http://www.cs.umd.edu/projects/plus/ec/ecj/ (2002)
Peng, J., Bhanu, B.: Closed-Loop Object Recognition Using Reinforcement Learning. IEEE Trans. on PAMI 20 (1998) 139–154
Platt, J.: Fast Training of Support Vector Machines using Sequential Minimal Optimization. In: Schölkopf, B., Burges, C., Smola, A. (eds.): Advances in Kernel Methods-Support Vector Learning. MIT Press, Cambridge, Mass. (1998)
Potter, M.A., De Jong, K.A.: Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents. Evolutionary Computation 8 (2000) 1–29
Quinlan, J.R.: C4.5: Programs for machine learning. Morgan Kaufmann, San Mateo, Calif. (1992)
Ross, T., Worell, S., Velten, V., Mossing, J., Bryant, M.: Standard SAR ATR Evaluation Experiments using the MSTAR Public Release Data Set. SPIE Proc.: Algorithms for Synthetic Aperture Radar Imagery V, Vol. 3370, Orlando, FL (1998) 566–573
Segen, J.: GEST: A Learning Computer Vision System that Recognizes Hand Gestures. In: Michalski, R.S., Tecuci, G., (eds.): Machine Learning. A Multistrategy Approach. Volume IV. Morgan Kaufmann, San Francisco, Calif. (1994) 621–634
Teller, A., Veloso, M.: A Controlled Experiment: Evolution for Learning Difficult Image Classification. Proc. 7th Portuguese Conference on Artificial Intelligence. Springer Verlag, Berlin, Germany (1995) 165–176
Wiegand, R.P., Liles, W.C., De Jong, K.A.: An Empirical Analysis of Collaboration Methods in Cooperative Coevolutionary Algorithms. Proc. Genetic and Evolutionary Computation Conference (GECCO 2001). Morgan Kaufmann, San Francisco, Calif. (2001) 1235–1242
Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco, Calif. (1999)
Wolpert, D., Macready, W.G.: No Free Lunch Theorems for Search. Tech. Report SFI-TR-95-010, The Santa Fe Institute (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Krawiec, K., Bhanu, B. (2003). Coevolution and Linear Genetic Programming for Visual Learning. In: Cantú-Paz, E., et al. Genetic and Evolutionary Computation — GECCO 2003. GECCO 2003. Lecture Notes in Computer Science, vol 2723. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45105-6_39
Download citation
DOI: https://doi.org/10.1007/3-540-45105-6_39
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40602-0
Online ISBN: 978-3-540-45105-1
eBook Packages: Springer Book Archive