http://de.evo-art.org/index.php?action=history&feed=atom&title=Cartesian_Genetic_Programming_for_Image_Processing_Tasks 2026-05-23T07:49:37Z Versionsgeschichte dieser Seite in de_evolutionary_art_org MediaWiki 1.27.4 http://de.evo-art.org/index.php?title=Cartesian_Genetic_Programming_for_Image_Processing_Tasks&diff=1671&oldid=prev 2014-11-23T20:55:17Z

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

Gbachelier