Training genetically evolving cellular automata for image processing
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 753-756 vol.2
- https://doi.org/10.1109/sipnn.1994.344802
Abstract
The paper describes the use of a genetically controlled automaton model to tackle image processing problems. A generalised system is set up that attempts to discover the precise cellular automaton functions required to solve a given problem. Functions are located with the help of a genetic algorithm, and once trained the system is able to process unseen images. The results have shown that the system correctly solves the task of image edge detection, and that the same procedure may be used for any image processing task.Keywords
This publication has 1 reference indexed in Scilit:
- A survey of two-dimensional automata theoryInformation Sciences, 1991