Abstract
This paper describes a domain independent approach to the use of neural networks (NNs) and genetic programming (GP) for object detection problems. Instead of using high level features for a particular task, this approach uses domain independent pixel statistics for object detection. The paper first compares an NN method and a GP method on four image data sets providing object detection problems of increasing difficulty. The results show that the GP method performs better than the NN method on these problems but still produces a large number of false alarms on the difficult problem and computation cost is still high. To deal with these problems, we develop a new method called GP-refine that uses a two stage learning process. The new GP method further improves object detection performance on the difficult detection task.
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
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) the PDP research group,: Parallel distributed Processing, Explorations in the Microstructure of Cognition: Foundations, vol. 1, The MIT Press, Cambridge (1986)
Koza, J.R.: Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge (1992)
Shirvaikar, M.V., Trivedi, M.M.: A network filter to detect small targets in high clutter backgrounds. IEEE Transactions on Neural Networks 6, 252–257 (1995)
Casasent, D.P., Neiberg, L.M.: Classifier and shift-invariant automatic target recognition neural networks. Neural Networks 8, 1117–1129 (1995)
Roberts, M.E., Claridge, E.: Cooperative coevolution of image feature construction and object detection. Technical report, University of Birmingham, School of Computer Science (2004)
Howard, D., Roberts, S.C., Brankin, R.: Target detection in SAR imagery by genetic programming. Advances in Engineering Software 30, 303–311 (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.) EvoWorkshops 2003, LNCS, vol. 2611, pp. 455–466. Springer, Heidelberg (2003)
The pascal object recognition database collection (2007), http://www.pascal-network.org/challenges/VOC/databases.html
Chin, B., Zhang, M.: Object detection using neural networks and genetic programming. Technical report, School of MSCS, Victoria University of Wellington (2007), http://www.mcs.vuw.ac.nz/comp/Publications/CS-TR-07-3.abs.html
Koza, J.R.: Genetic Programming II: Automatic Discovery of Reusable Programs. MIT Press, Cambridge (1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chin, B., Zhang, M. (2008). Object Detection Using Neural Networks and Genetic Programming. In: Giacobini, M., et al. Applications of Evolutionary Computing. EvoWorkshops 2008. Lecture Notes in Computer Science, vol 4974. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78761-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-540-78761-7_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78760-0
Online ISBN: 978-3-540-78761-7
eBook Packages: Computer ScienceComputer Science (R0)