Understanding Evolved Genetic Programs for a Real World Object Detection Problem
We describe an approach to understanding evolved programs for a real world object detection problem, that of finding orthodontic landmarks in cranio-facial X-Rays. The approach involves modifying the fitness function to encourage the evolution of small programs, limiting the function set to a minimal number of operators and limiting the number of terminals (features). When this was done for two landmarks, an easy one and a difficult one, the evolved programs implemented a linear function of the features. Analysis of these linear functions revealed that underlying regularities were being captured and that successful evolutionary runs usually terminated with the best programs implementing one of a small number of underlying algorithms. Analysis of these algorithms revealed that they are a realistic solution to the object detection problem, given the features and operators available.
Unable to display preview. Download preview PDF.
- 4.Ciesielski, V., Innes, A., Mamutil, J., John, S.: Landmark detection for cephalometric radiology images using genetic programming. International Journal of Knowledge Based Intelligent Engineering Systems 7(3), 164–171 (2003)Google Scholar
- 7.Innes, A., Ciesielski, V., Mamutil, J., John, S.: Landmark detection for cephalometric radiology images using pulse coupled neural networks. In: Arabnia, H., Mun, Y. (eds.) Proceedings of the International Conference on Artificial Intelligence (IC-AI 2002), Las Vegas, June 2002, vol. 2, pp. 511–517. CSREA Press (2002)Google Scholar