Visual Learning by Evolutionary Feature Synthesis
Inhaltsverzeichnis
Reference
Krzysztof Krawiec and Bir Bhanu: Visual Learning by Evolutionary Feature Synthesis. Proceedings of the Twentieth International Conference on Machine Learning (ICML 2003), pp. 376-383, AAAI Press, August 21-24 2003.
DOI
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.
Extended Abstract
Bibtex
Used References
Banzhaf, W., Nordin, P., Keller, R., & Francone, F. (1998). Genetic programming. An introduction. On the automatic evolution of computer programs and its application. San Francisco: Morgan Kaufmann.
Bhanu, B. & Krawiec, K. (2002). Coevolutionary construction of features for transformation of representation in machine learning. Proceedings of Genetic and Evolutionary Computation Conference (Workshop on Coevolution). New York: AAAI Press, 249-254.
Draper, B., Hanson, A., & Riseman, E. (1993). Learning blackboard-based scheduling algorithms for computer vision. International Journal of Pattern Recognition and Artificial Intelligence, 7, 309-328.
Intel® image processing library: Reference manual. Intel Corporation, 2000.
Johnson, M.P. (1995). Evolving visual routines. Master’s Thesis, Massachusetts Institute of Technology.
Krawiec, K. (2001). Pairwise comparison of hypotheses in evolutionary learning. In: C.E. Brodley, & A. Pohoreckyj Danyluk (Eds.), Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann, 266-273.
Luke, S. (2002). ECJ Evolutionary Computation System. http://www.cs.umd.edu/projects/plus/ec/ecj/.
Maloof, M.A., Langley, P., Binford, T.O., Nevatia, R., & Sage, S. (2003). Improved rooftop detection in aerial images with machine learning. Machine Learning (in press).
Matheus, C.J. (1989). A constructive induction framework. Proceedings of the Sixth International Workshop on Machine Learning. New York: Ithaca, 474-475.
Open source computer vision library: Reference manual. Intel Corporation, 2001.
Peng, J. & Bhanu, B. (1998a). Closed-loop object recognition using reinforcement learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 139-154.
Peng, J. & Bhanu, B. (1998b). Delayed Reinforcement Learning for Adaptive Image Segmentation and Feature Extraction. IEEE Transactions on Systems, Man and Cybernetics, 28, 482-488, August 1998.
Poli, R. (1996). Genetic programming for image analysis. (Technical Report CSRP-96-1). University of Birmingham.
Potter, M.A. & De Jong, K.A. (2000). Cooperative coevolution: an architecture for evolving coadapted subcomponents. Evolutionary Computation, 8, 1-29.
Rizki, M., Zmuda, M., & Tamburino, L. (2002). Evolving pattern recognition systems. IEEE Transactions on Evolutionary Computation, 6, 594-609.
Ross, T., Worell, S., Velten, V., Mossing, J., & Bryant, M. (1998). Standard SAR ATR evaluation experiments using the MSTAR public release data set. SPIE Proceedings: Algorithms for Synthetic Aperture Radar Imagery V, Vol. 3370, Orlando, FL, 566-573.
Segen, J. (1994). GEST: A learning computer vision system that recognizes hand gestures. In R.S. Michalski, & G. Tecuci (Eds.), Machine learning. A Multistrategy Approach. Volume IV. San Francisco: Morgan Kaufmann, 621-634.
Teller, A. & Veloso, M. (1995). A controlled experiment: evolution for learning difficult image classification. Lecture Notes in Computer Science, Vol. 990, 165-185.
Wiegand, R.P., Liles, W.C., & De Jong, K.A. (2001). An empirical analysis of collaboration methods in cooperative coevolutionary algorithms. Proceedings of Genetic and Evolutionary Computation Conference, San Francisco: Morgan Kaufmann, 1235-1242.
Witten, I.H. & Frank, E. (1999). Data mining: Practical machine learning tools and techniques with Java implementations, San Francisco: Morgan Kaufmann.
Wolpert, D. & Macready, W.G. (1997). No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation, 1, 67-82.
Links
Full Text
http://www.aaai.org/Papers/ICML/2003/ICML03-051.pdf
