Face Detection Using Particle Swarm Optimization and Support Vector Machines
In this paper, a face detection algorithm that uses Particle Swarm Optimization (PSO) for searching the image is proposed. The algorithm uses a linear Support Vector Machine (SVM) as a fast and accurate classifier in order to search for a face in the two-dimension solution space. Using PSO, the exhaustive search in all possible combinations of the 2D coordinates can be avoided, saving time and decreasing the computational complexity. Moreover, linear SVMs have proven their efficiency in classification problems, especially in demanding applications. Experimental results based on real recording conditions from the BioID database are very promising and support the potential use of the proposed approach to real applications.
Unable to display preview. Download preview PDF.
- 1.Goldmann, L., Mönich, U., Sikora, T.: Components and their topology for robust face detection in the presence of partial occlusions. IEEE Transactions on Information Forensics and Security 2(3) (September 2007)Google Scholar
- 4.Burges, C.: A tutorial on support vector machines for pattern recognition. Kluwer Academic Publishers, Boston (1998)Google Scholar
- 5.Kasturi, R., Goldgof, D., Soundararajan, P., Manohar, V., Garofolo, J., Bowers, R., Boonstra, M., Korzhova, V., Zhang, J.: Framework for performance evaluation of face, text, and vehicle detection and tracking in video: Data, metrics, and protocol. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(2), 319–336 (2009)CrossRefGoogle Scholar