Evolving Low-Level Vision Capabilities with the GENCODER Genetic Programming Environment
A new approach for the application of genetic programming to vision problems is presented. Sets of atomic subprograms are genetically combined to solve more advanced problems within low-level vision or image preprocessing. We present the main ideas and give a brief sketch of their implementation in the distributed simulation environment GENCODER. This system forms the basis for some introductory experiments obtained. Finally, some aspects of the gained results together with interesting possibilities for future research are portrayed.
KeywordsGenetic Program Source Image Visual Module Good Program Early Vision
Unable to display preview. Download preview PDF.
- J. Aloimonos and D. Shulman. ‘Integration of Visual Modules — An Extension of the Marr Paradigm’. Academic Press, 1989.Google Scholar
- J. Koza. ‘Genetic Programming — On the Programming of Computers by Means of Natural Selection’. MIT Press, 1992.Google Scholar
- T. Poggio, V. Torre, and C. Koch. ‘Computational vision and regularization theory’. Nature 317, 1985.Google Scholar