Abstract
The problem of optimizing classifiers for object detection has already been discussed in several publications. In order to achieve better results, it was decided to use genetic algorithms to optimize the classifiers. By applying this approach optimization is automatic in respect to image (or group of images). For test issues the haar-like object detection features were used. Genetic model has been created over the field of solutions and evolved to provide better results. Proposed algorithm was tested and results are presented. The proposed solution can be applied to another type of classifier and adapted to optimize any detection parameter.
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
Viola, P., Jones, M.: Rapid object detection using boosted cascade of simple features. Computer Vision and Pattern Recognition, 511â518 (2001)
Viola, P., Jones, M.: Robust Real-time Object Detection. In: Second International Workshop on Statistical and Computational Theories of Vision â Modeling, Learning, Computing and Sampling, Vancouver, Canada, July 13 (2001)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: VitĂĄnyi, P.M.B. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23â37. Springer, Heidelberg (1995)
Lienhart, R., Liang, L., Kuranov, A.: A detector tree of boosted classifiers for real-time object detection and tracking. In: International Conference Multimedia and Expo (ICME 2003) (2003)
Holland, J.H.: Adaptation in Nature and Artificial Systems. The University of Michigan Press (1975)
Open source computer vision library (2011.03.01), http://opencv.willowgarage.com/
Byron Katie Blog 2011.03.01, http://www.byronkatie.com/
Sackler Institute 2003 (2011.03.01), http://www.sacklerinstitute.org/cornell/summer_institute/2003/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
MatiolaĆski, A., Guzik, P. (2011). Automated Optimization of Object Detection Classifier Using Genetic Algorithm. In: Dziech, A., CzyĆŒewski, A. (eds) Multimedia Communications, Services and Security. MCSS 2011. Communications in Computer and Information Science, vol 149. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21512-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-21512-4_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21511-7
Online ISBN: 978-3-642-21512-4
eBook Packages: Computer ScienceComputer Science (R0)