Visual Learning by Evolutionary and Coevolutionary Feature Synthesis

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Reference

Krzysztof Krawiec and Bir Bhanu: Visual Learning by Evolutionary and Coevolutionary Feature Synthesis. IEEE Transactions on Evolutionary Computation, 11(5), pp. 635-650, October 2007.

DOI

http://dx.doi.org/10.1109/TEVC.2006.887351

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. 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 at the genotype level. The training coevolves feature extraction procedures, each being a sequence of elementary image processing and computer vision operations applied to input images. Extensive experimental results show that the approach attains competitive performance for three-dimensional object recognition in real synthetic aperture radar imagery.

Extended Abstract

Bibtex

Used References

W. Banzhaf , P. Nordin , R. Keller and F. Francone Genetic Programming. An Introduction. on the Automatic Evolution of Computer Programs and Its Application, 1998 :Morgan Kaufmann

B. Bhanu , D. E. Dudgeon , E. G. Zelnio , A. Rosenfeld , D. Casasent and I. S. Reed "Introduction to the special issue on automatic target detection and recognition", IEEE Trans. Image Process., vol. 6, no. 1, pp.1 -6 1997

B. Bhanu and K. Krawiec "Coevolutionary construction of features for transformation of representation in machine learning", Proc. Genetic and Evol. Comput. Conf., pp.249 -254 2002

B. Bhanu and S. Lee Genetic Learning for Adaptive Image Segmentation, 1994 :Kluwer

B. Bhanu and J. Peng "Adaptive integrated image segmentation and object recognition", IEEE Trans. Syst., Man, Cybern.-Part C, vol. 30, pp.427 -441 2000 http://dx.doi.org/10.1109/5326.897070

B. Bhanu , Y. Lin and K. Krawiec Evolutionary Synthesis of Pattern Recognition Systems, 2005 :Springer-Verlag

B. Draper , A. Hanson and E. Riseman "Learning blackboard-based scheduling algorithms for computer vision", Int. J. Pattern Recogn. Artif. Intell., vol. 7, pp.309 -328 1993 http://dx.doi.org/10.1142/S0218001493000169

J. Y. Goulermas and P. Liatsis "A collective-based symbiotic model for surface reconstruction in area-based stereo", IEEE Trans. Evol. Comput., vol. 7, no. 5, pp.482 -502 2003 http://dx.doi.org/10.1109/TEVC.2003.817460

Intel Image Processing Library, 2000

M. P. Johnson , P. Maes and T. Darrell R. A. Brooks and P. Maes "Evolving visual routines", Proc. 4th Int. Workshop Synthesis and Simulation of Living Systems: Artificial Life IV, pp.373 -390 1994

J. R. Koza , D. Andre , F. H. Bennett IIIand M. A. Keane Genetic Programming III: Darwinian Invention and Problem Solving, 1999 : Morgan Kaufmann

K. Krawiec C. E. Brodley and A. P. Danyluk "Pairwise comparison of hypotheses in evolutionary learning", Proc. 18th Int. Conf. Mach. Learn., pp.266 -273 2001 http://dx.doi.org/10.1007/3-540-44596-X_25

K. Krawiec and B. Bhanu "Visual learning by coevolutionary feature synthesis", IEEE Trans. Syst., Man, Cybern.-Part B, vol. 35, pp.409 -425 2005 http://dx.doi.org/10.1109/TSMCB.2005.846644

K. Krawiec and B. Bhanu E. Cantú-Paz Lecture Notes in Computer Science, vol. 2723, pp.332 -343 2003 :Springer-Verlag

J. R. Levenick "Inserting introns improves genetic algorithm success rate: Taking a cue from biology", Proc. 4th Int. Conf. Genetic Algorithms, pp.123 -127 1991

Y. Lin and B. Bhanu "Evolutionary feature synthesis for object recognition", IEEE Trans. Syst., Man, Cybern., Part C, vol. 35, no. 2, pp.156 -171 2005 http://dx.doi.org/10.1109/TSMCC.2004.841912

S. Luke ECJ evolutionary computation system,, 2002. [online] Available: http://www.cs.umd.edu/projects/plus/ec/ecj/


M. A. Maloof , P. Langley , T. O. Binford , R. Nevatia and S. Sage "Improved rooftop detection in aerial images with machine learning", Mach. Learn., vol. 53, pp.157 -191 2003 http://dx.doi.org/10.1023/A:1025623527461

C. J. Matheus "A constructive induction framework", Proc. 6th Int. Workshop Mach. Learn., pp.474 -475 1989

Z. Michalewicz Genetic Algorithms+Data Structures=Evolution Programs, 1996 :Springer-Verlag

Open Source Computer Vision Library, 2001

J. Peng and B. Bhanu "Closed-loop object recognition using reinforcement learning", IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 2, pp.139 -154 1998 http://dx.doi.org/10.1109/34.659932

J. Peng and B. Bhanu "Delayed reinforcement learning for adaptive image segmentation and feature extraction", IEEE Trans. Syst., Man, Cybern., vol. 28, no. 3, pp.482 -488 1998 http://dx.doi.org/10.1109/5326.704593

R. Poli J. R. Koza "Genetic programming for image analysis", Proc. 1st Int. Conf. Genetic Program., pp.363 -368 1996

M. A. Potter and K. A. De Jong "Cooperative coevolution: An architecture for evolving coadapted subcomponents", Evol. Comput., vol. 8, pp.1 -29 2000 http://dx.doi.org/10.1162/106365600568086

J. R. Quinlan C4.5: Programs for Machine Learning, 1999 :Morgan Kaufmann

M. Rizki , M. Zmuda and L. Tamburino "Evolving pattern recognition systems", IEEE Trans. Evol. Comput., vol. 6, no. 6, pp.594 -609 2002 http://dx.doi.org/10.1109/TEVC.2002.806167

T. Ross , S. Worell , V. Velten , J. Mossing and M. Bryant "Standard SAR ATR evaluation experiments using the MSTAR public release data set", Proc. SPIE: Algorithms for Synthetic Aperture Radar Imagery V, vol. 3370, pp.566 -573 1998 http://dx.doi.org/10.1117/12.321859

J. Segen R. S. Michalski and G. Tecuci Machine Learning. A Multistrategy Approach. Volume IV, pp.621 -634 1994 :Morgan Kaufmann

A. Teller and M. M. Veloso K. Ikeuchi and M. Veloso Symbolic Visual Learning, pp.77 -112 1997

R. P. Wiegand , W. C. Liles and K. A. De Jong "An empirical analysis of collaboration methods in cooperative coevolutionary algorithms", Proc. Genetic and Evol. Comput. Conf., pp.1235 -1242 2001

I. H. Witten and E. Frank Data Mining: Practical Machine Learning Tools and Techniques With Java Implementations, 1999 :Morgan Kaufmann

D. Wolpert and W. G. Macready "No free lunch theorems for optimization", IEEE Trans. Evol. Comput., vol. 1, no. 1, pp.67 -82 1997 http://dx.doi.org/10.1109/4235.585893


Links

Full Text

[extern file]

intern file

Sonstige Links