Evolutionary Learning of Primitive-Based Visual Concepts
Inhaltsverzeichnis
Reference
Krzysztof Krawiec: Evolutionary Learning of Primitive-Based Visual Concepts. Proceedings of the 2006 IEEE Congress on Evolutionary Computation, pp. 4451-4458, IEEE Press, 6-21 July 2006.
DOI
http://dx.doi.org/10.1109/CEC.2006.1688460
Abstract
The paper presents a novel method of evolutionary learning dedicated to acquisition of visual concepts. The learning process takes place in a population of genetic programming-based learners that process attributed visual primitives derived from raw raster images. The approach uses an original evaluation scheme: evolving individuals-learners are rewarded for being able to sketch the input visual stimulus. Recognition proceeds here as an attempt of restoring essential features of the input image. The approach is general by being based mostly on universal vision knowledge; only very limited amount of a priori knowledge about the particular application or target concept to be learned is required. We explain the method in detail and verify it experimentally on acquisition of simple visual concepts (triangle and section) from examples.
Extended Abstract
Bibtex
Used References
Java advanced imaging API specification, version 1.2. Tech. rep., 2001.
BHANU, B., LIN, Y., AND KRAWIEC, K. Evolutionary Synthesis of Pattern Recognition Systems. Springer-Verlag, New York, 2005.
DRAPER, B., HANSON, A., AND RISEMAN, E. Learning blackboard-based scheduling algorithms for computer vision. Int. J. of Pattern Recognition and Artificial Intelligence 7 (March 1993), 309-328. http://dx.doi.org/10.1142/S0218001493000169
JOHNSON, M., MAES, P., AND DARRELL, T. Evolving visual routines. In Artificial Life IV: Proc of the 4 th international workshop on the synthesis and simulation of living systems (Cambridge, MA, 1994), R. Brooks and P. Maes, Eds., MIT Press, pp. 373-390.
KOZA, J. Genetic programming - 2. MIT Press, Cambridge, MA, 1994.
KRAWIEC, K. Learning high-level visual concepts using attributed primitives and genetic programming. In EvoWorkshops 2006 (Berlin Heidelberg, 2006), F. Rothlauf, Ed., LNCS 3907, Springer-Verlag, pp. 515-519.
KRAWIEC, K., AND BHANU, B. Visual learning by coevolutionary feature synthesis. IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics 35 (2005), 409-425. http://dx.doi.org/10.1109/TSMCB.2005.846644
LUKE, S. ECJ evolutionary computation system, 2002. (http://cs.gmu.edu/eclab/projects/ecj/).
MALOOF, M., LANGLEY, P., BINFORD, T., NEVATIA, R., AND SAGE, S. Improved rooftop detection in aerial images with machine learning. Machine Learning 53 (2003), 157-191. http://dx.doi.org/10.1023/A:1025623527461
OGIELA, M., AND TADEUSIEWICZ, R. Nonlinear processing and semantic content analysis in medical imaging - a cognitive approach. IEEE Transactions on Instrumentation and Measurement 54 (Dec. 2005), 2149-2155. http://dx.doi.org/10.1109/TIM.2005.858566
RLZKI, M., ZMUDA, M., AND TAMBURINO, L. Evolving pattern recognition systems. IEEE Transactions on Evolutionary Computation 6 (2002), 594-609.
SEGEN, J. GEST: A learning computer vision system that recognizes hand gestures. In Machine learning. A Multistrategy Approach. Volume IV, R. Michalski and G. Tecuci, Eds. Morgan Kaufmann, San Francisco, CA, 1994, pp. 621-634.
TELLER, A., AND VELOSO, M. PADO: A new learning architecture for object recognition. In Symbolic Visual Learning, K. Ikeuchi and M. Veloso, Eds. Oxford Press, New York, 1997, pp. 77-112. TORRALBA, A., MURPHY, K., AND FREEMAN, W. MIT-CSAIL computer vision annotated image library. Tech. rep., http://web.mit.edu/torralba/www/database.html, 2004.
