Genetic Programming for Image Analysis
Inhaltsverzeichnis
Reference
Riccardo Poli: Genetic Programming for Image Analysis. TR Number CSRP-96-1, January 1996.
DOI
Abstract
This paper describes an approach to us- ing GP for image analysis based on the idea that image enhancement, feature de- tection and image segmentation can be re-framed as filtering problems. GP can discover efficient optimal filters which solve such problems but in order to make the search feasible and effective, termi- nal sets, function sets and fitness func- tions have to meet some requirements. We describe these requirements and we propose terminals, functions and fitness functions that satisfy them. Experiments are reported in which GP is applied to the segmentation of the brain in medi- cal images and is compared with artifi- cial neural nets.
Extended Abstract
Bibtex
Used References
[Andre, 1994] Andre, D. (1994). Automatically defined fea- tures: the simulataneous evolution of 2-dimensional fea- ture detectors and an algorithm for using them. In K. E. Kinnear, Jr., editor, Advances in Genetic Programming, chapter 23, pages 477–494. MIT Press.
[Ballard and Brown, 1982] Ballard, D. and Brown, C. (1982). Computer Vision. Prentice-Hall, Englewood Cliff, NJ.
[Breunig, 1995] Breunig, M. M. (1995). Location indepen- dent pattern recognition using genetic programming. In Koza, J. R., editor, Genetic Algorithms and Genetic Pro- gramming at Stanford 1995, pages 29–38. Stanford Book- store, Stanford University.
[Coppini et al., 1992] Coppini, G., Poli, R., Rucci, M., and Valli, G. (1992). A neural network architecture for under- standing 3D scenes in medical imaging. Computer and Biomedical Research, 25:569–585.
[K. E. Kinnear, Jr., 1994] K. E. Kinnear, Jr., editor (1994). Advances in Genetic Programming. MIT Press.
[Koza, 1992] Koza, J. R. (1992). Genetic Programming: On the Programming of Computers by Means of Natural Se- lection. MIT Press.
[Koza, 1994] Koza, J. R. (1994). Genetic Programming II: Automatic Discovery of Reusable Programs. MIT Pres, Cambridge, Massachusetts.
[Poli and Valli, 1996] Poli, R. and Valli, G. (1996). Hop- field neural nets for the optimum segmentation of medical images. In Fiesler, E. and Beale, R., editors, Handbook of Neural Computation, chapter G.5.5. Oxford University Press. (in press).
[Riolo and Line, 1995] Riolo, R. L. and Line, M. P. (1995). Automatic discovery of classification and estimation algo- rithms for earth-observation satellite imagery. In Siegel, E. S. and Koza, J. R., editors, Working Notes for the AAAI Symposium on Genetic Programming, pages 73–77, MIT, Cambridge, MA, USA. AAAI.
[Tackett, 1993] Tackett, W. A. (1993). Genetic programming for feature discovery and image discrimination. In Inter- national Conference on Genetic Algorithms.
[Teller and Veloso, 1995] Teller, A. and Veloso, M. (1995). A controlled experiment: Evolution for learning difficult image classification. In Seventh Portuguese Conference On Artificial Intelligence. Springer-Verlag.
Links
Full Text
http://cswww.essex.ac.uk/staff/rpoli/papers/Poli-GP1996.pdf
