A GP Artificial Ant for image processing: preliminary experiments with EASEA.
This paper describes how animat-based “food foraging” techniques may be applied to the design of low-level image processing algorithms. First, we show how we implemented the food foraging application using the EASEA software package. We then use this technique to evolve an animat and learn how to move inside images and detect high-gradient lines with a minimum exploration time. The resulting animats do not use standard “scanning + filtering” techniques but develop other image exploration strategies close to contour tracking. Experimental results on grey level images are presented.
KeywordsFitness Function Grey Level Image Contour Detection Left Turn CMOS Image Sensor
Unable to display preview. Download preview PDF.
- D.H. Ballard and C.M. Brown, Computer Vision, Prentice Hall, 1982.Google Scholar
- V. Cantoni, M. Ferretti, S. Levialdi, R. Negrini and S. Stefanelli, Progress in Image Analysis and Processing, World Scientific,1991.Google Scholar
- R.J. Collins and D.R. Jefferson. Antfarm: Towards simulated evolution. In S. Rasmussen, J. Farmer, C. Langton and C. Taylor, editors, Artificial Life II, Reading, Massachusetts, Addison-Wesley, 1991.Google Scholar
- F.L. Crabbe, Michael G. Dyer, Observation and Imitation: Goal Sequence Learning in Neurally Controlled Construction Animats: VI-MAXSON, SAB 2000, Paris.Google Scholar
- EASEA (EAsy Specification of Evolutionary Algorithms) home page: http://www-rocq.inria.fr/EASEA/
- EO (Evolutionary Objects) home page: http://www.geneura.ugr.es/~jmerelo/EO.html
- GAlib home page: http://www.lancet.mit.edu/ga/
- P. Gaussier. Autonomous Robots interacting with an unknown world, Special Issue on Animat Approach to Control, Robotics and Autonomous Systems, 16, 1995.Google Scholar
- R.C. Gonzalez, R.E. Woods, Digital Image Processing, Wiley, 1992Google Scholar
- J. Ivins, J. Porrill, Statistical Snakes: Active Region Models, British Machine Vision Conference, York, Sep. 1994.Google Scholar
- R.C. Jain, R. Kasturi, B.G. Schunck, Machine Vision, McGraw-Hill, 1995.Google Scholar
- D. Jefferson, R. Collins, C. Cooper, M. Dyer, M. Flower, R. Korf, C. Taylor, A. Wang, Evolution as a theme in artificial life: the Genesys/Tracker system, Artificial life II, vol. X, Santa Fe Institute Studies in the Sciences of Complexity, Addison-Wesley, Feb. 1992, 549–578.Google Scholar
- M. Köppen, B. Nickolay, Design of image exploring agent using genetic programming, Proceedings of the 4th International Conference on Soft Computing, volume 2, pages 549–552, Fukuoka, Japan, 30 Sep–5 Oct 1996, World Scientific, Singapore.Google Scholar
- J.R. Koza, Genetic Programming, MIT Press 1992.Google Scholar
- I. Kuscu, A genetic Constructive Induction Model. In P.J. Angeline, Z. Michalewicz, M. Schoenauer, Xin Yao, and A. Zalzala, editors, Proceedings of the Congress on Evolutionary Computation, volume 1, pages 212–217, Mayflower Hotel, Washington D.C., USA, 6–9 July 1999. IEEE Press.Google Scholar
- W.B. Langdon, Genetic Programming and Data Structures: Genetic Programming + Data Structures = Automatic Programming !, Kluwer, 1998.Google Scholar
- W.B. Langdon and R. Poli, Better Trained Ants for Genetic Programming, Technical Report CSRP-98-12, April 1998, http://www.cs.bham.ac.uk/wbl.
- W.B. Langdon and R. Poli, Why Ants are Hard, Technical Report: CSRP-98-4, January 1998, http://www.cs.bham.ac.uk/wbl.
- J. Lévy Vehel, introduction to the multifractal analysis of images, in Fractal image encoding and analysis, Yuval Fischer ed., Springer Verlag, 1996.Google Scholar
- J.A. Meyer, A. Guillot, From SAB90 to SAB94: Four Years of Animat Research, Proceedings of Third International Conference on Simulation of Adaptive Behavior. Brighton, England, 1994.Google Scholar
- R. Moller, D. Lambrinos, R. Pfeifer, T. Labhart, and R. Wehner, Modeling Ant Navigation with an Autonomous Agent, From Animals to Animats 5, Proc. of the 5th Int. Conf. on Simulation of Adaptive Behavior, August 17-21, 1998, Zurich, Switzerland, edited by R. Pfeifer, B. Blumberg, J.-A. Meyer and S.W. Wilson.Google Scholar
- S.W. Wilson, Classifier systems and the animat problem, Machine Learning 2 (1987), 199–228.Google Scholar
- S.W. Wilson, (1991). The animat approach to AI. In J. Meyer & S.W. Wilson (Eds), From Animals to Animats, Proceedings of the first International Conference on Simulation of Adaptive Behavior, Cambridge, MA: MIT Press, 15–21.Google Scholar
- M. Witkowski, The Role of Behavioral Extinction in Animat Action Selection, SAB 2000, Paris, 2000.Google Scholar