Cartesian Genetic Programming for Image Processing Tasks
Inhaltsverzeichnis
Reference
H. A. Montes and J. L. Wyatt: Cartesian Genetic Programming for Image Processing Tasks. Proceedings of Neural Networks and Computational Intelligence, NCI 2003, IASTED, 19-21 May 2003.
DOI
Abstract
This paper presents experimental results on image analysis for a particular form of Genetic Programming called Cartesian Ge- netic Programming (CGP) in which programs use the structure of a graph represented as a linear sequence of integers. The efficency of this approach is investigated for the problem of Object Localization in a given image. This task is usually car- ried out by applying a series of well known image processing operators and commonly relies on the skills and expertise of the researchers. In this work, we present results from a num- ber of runs on actual camera images, in which a set of fairly simple primitives were investigated.
Extended Abstract
Bibtex
Used References
[1] J. Andrade-Cetto and A. Kak. Object recogni- tion. Wiley Encyclopedia of Electrical and Elec- tronics Engineering, vol. supplement 1:449—470, 2000.
S. P. Brumby, J. Theiler, S. J. Perkins, N. Harvey, J. J. Szymanski, J. J. Bloch, and M. Mitchell. Investigation of image feature exs- traction by a genetic algorithm. Proceedings SPIE, pages 24—31, 1999.
[3] J. Daida, T. F. Bersano-Begey, S. J. Ross, and J. F. Vesecky. Evolving feature extraction algo- rithms: Adapting genetic programming for im- age analysis in geoscience and remote sensing. Proceedings of IGARSS’96, 1996.
[4] J. Daida, J. D. Hommes, T. F. Bersano-Begey, S. J. Ross, and J. F. Vesecky. Algorithm dis- covery using the genetic programming paradigm: extracting low-contrast curvilinear features from the SAR images of the artic ice. Advances in Ge- netic Programming, pages 417—442, 1996.
[5] M. Ebner. On the evolution of interest oper- ators using genetic programming. Late Bark- ing Papers at EuroGP’98: The First European Workshop on Genetic Programming, pages 6—10, 1998.
[6] M. Ebner and A. Zell. Evolving a task specific image operator. Proceedings of the First Eu- ropean Workshop on Evolutionary Image Anal- ysis, Signal Processing and Telecomunications (EvoIASP’99 and EuroTel’99), pages 74—89, 1999.
H. V. Hove and A. Verschoren. Genetic algo- rithms and recognition problems. Genetic Algo- rithms for Pattern Recognition, pages 145—166, 1996.
M. P. Johnson, P. Maes, and T. Darrell. Evolv- ing visual routines. Artificial Life IV, Proceed- ing of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, pages 198—209, 1994.
M. C. Martin. The Simulated Evolution of Robot Perception. PhD thesis, Carnegie Mellon Univer- sity, Pittsburgh, PA, June 2001.
J. F. Miller and P. Thomson. Cartesian ge- netic programming. In Proceeding of the Third European Conference on Genetic Programming, 1802:121—132, 15-16 April 2000.
R. Poli. Parallel distributed genetic program- ming. Technical Report CSRP-96-12, School of Computer Science, University of Birmingham, U.K., 1996.
[12] R. Poli and S. Canogni. Genetic programming with user-driven selection: Experiments on the evolution of algorithms for image enhancement. Genetic Programming 1997, Proceedings of the Second Annual Conference, pages 269—277, 1997.
[13] H. P. Schwefel. Evolution and Optimum Seeking. Sixth-Generation Computer Technology. Wiley, New York, 1995.
[14] W. A. Tackett. Genetic programming for fea- ture discovering and image discrimination. Pro- ceedings of the Fifth International Conference on Genetic Algorithms, pages 303—309, 1993.
[15] A. Teller. Algorithm Evolution with Internal Re- inforcement for Signal Understanding. PhD the- sis, School of computer science, Carnegie Mellon University, Pittsburgh, PA, 1998.
[16] A. Teller and M. Veloso. Algorithm evolution for face recognition: What makes a picture diffi- cult. International Conference on Evolutionary Computation, pages 608—613, 1995.
[17] A. Teller and M. Veloso. PADO: Learning tree structured algorithms for orchestration into an object recognition system. Technical Report CMU-CS-95-101, Deparment of Computer Sci- ence, Carnegie Mellon University, Pittsburgh, PA, USA, 1995.
[18] I. Yoda, K. Yamamoto, and H. Yamada. An automatic acquisition of hierarchical mathemat- ical morphology procedures by GA. Proceedings of the 12th IAPR International Conference on Pattern Recognition, vol 2:421—425, 1994.
Links
Full Text
http://www.cs.bham.ac.uk/~nah/bibtex/papers/montes03cartesian.pdf
