Abstract
This paper describes two innovations that improve the efficiency and effectiveness of a genetic programming approach to object detection problems. The first innovation is to break the GP search into two phases with the first phase applied to a selected subset of the training data, and a simplified fitness function. The second phase is initialised with the programs from the first phase, and uses the full set of training data to construct the final detection programs. The second innovation is to add a program size component to the fitness function. Application of this approach to three object detection problems indicated that the innovations increased both the effectiveness and the efficiency of the genetic programming search.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Banzhaf, W., Nordin, P., Keller, R.E., Francone, F.D.: Genetic Programming: An Introduction on the Automatic Evolution of computer programs and its Applications. Morgan Kaufmann Publishers, San Francisco (1998)
Koza, J.R.: Genetic programming: on the programming of computers by means of natural selection. MIT Press, London (1992)
Tackett, W.A.: Genetic programming for feature discovery and image discrimination. In: Forrest, S. (ed.) Proceedings of the 5th International Conference on Genetic Algorithms, pp. 303–309. Morgan Kaufmann, San Francisco (1993)
Benson, K.: Evolving finite state machines with embedded genetic programming for automatic target detection within SAR imagery. In: Proceedings of the 2000 Congress on Evolutionary Computation, pp. 1543–1549. IEEE Press, Los Alamitos (2000)
Graae, C.T.M., Nordin, P., Nordahl, M.: Stereoscopic vision for a humanoid robot using genetic programming. In: Oates, M.J., Lanzi, P.L., Li, Y., Cagnoni, S., Corne, D.W., Fogarty, T.C., Poli, R., Smith, G.D. (eds.) EvoIASP 2000, EvoWorkshops 2000, EvoFlight 2000, EvoSCONDI 2000, EvoSTIM 2000, EvoTEL 2000, and EvoROB/EvoRobot 2000. LNCS, vol. 1803, pp. 12–21. Springer, Heidelberg (2000)
Howard, D., Roberts, S.C., Ryan, C.: The boru data crawler for object detection tasks in machine vision. In: Cagnoni, S., Gottlieb, J., Hart, E., Middendorf, M., Raidl, G.R. (eds.) EvoIASP 2002, EvoWorkshops 2002, EvoSTIM 2002, EvoCOP 2002, and EvoPlan 2002. LNCS, vol. 2279, pp. 220–230. Springer, Heidelberg (2002)
Lindblad, F., Nordin, P., Wolff, K.: Evolving 3d model interpretation of images using graphics hardware. In: Proceedings of the 2002 IEEE Congress on Evolutionary Computation. IEEE Press, Los Alamitos (2002)
Zhang, M., Ciesielski, V.: Genetic programming for multiple class object detection. In: Foo, N.Y. (ed.) Canadian AI 1999. LNCS, vol. 1747, pp. 180–192. Springer, Heidelberg (1999)
Zhang, M., Andreae, P., Pritchard, M.: Pixel statistics and false alarm area in genetic programming for object detection. In: Raidl, G.R., Cagnoni, S., Cardalda, J.J.R., Corne, D.W., Gottlieb, J., Guillot, A., Hart, E., Johnson, C.G., Marchiori, E., Meyer, J.-A., Middendorf, M. (eds.) EvoIASP 2003, EvoWorkshops 2003, EvoSTIM 2003, EvoROB/EvoRobot 2003, EvoCOP 2003, EvoBIO 2003, and EvoMUSART 2003. LNCS, vol. 2611, pp. 455–466. Springer, Heidelberg (2003)
Zhang, M., Ciesielski, V., Andreae, P.: A domain independent window-approach to multiclass object detection using genetic programming. EURASIP Journal on Signal Processing, Special Issue on Genetic and Evolutionary Computation for Signal Processing and Image Analysis 2003, 841–859 (2003)
Smith, P.W.H.: Controlling code growth in genetic programming. In: John, R., Birkenhead, R. (eds.) Advances in Soft Computing, De Montfort University, Leicester, UK, pp. 166–171. Physica-Verlag, Heidelberg (2000)
Dallaway, R.: Genetic programming and cognitive models. Technical Report CSRP 300, School of Cognitive & Computing Sciences, University of Sussex, Brighton, UK (1993)
Soule, T., Foster, J.A.: Effects of code growth and parsimony pressure on populations in genetic programming. Evolutionary Computation 6, 293–309 (1998)
Bhowan, U.: A domain independent approach to multi-class object detection using genetic programming. BSc Honours research project/thesis, School of Mathematical and Computing Sciences, Victoria University of Wellington (2003)
Ny, B.: Multi-class object classification and detection using neural networks. BSc Honours research project/thesis, School of Mathematical and Computing Sciences, Victoria University of Wellington (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, M., Andreae, P., Bhowan, U. (2004). A Two Phase Genetic Programming Approach to Object Detection. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science(), vol 3215. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30134-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-540-30134-9_32
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23205-6
Online ISBN: 978-3-540-30134-9
eBook Packages: Springer Book Archive