Abstract
We present an automatic face identification system using an unsupervised optimal clustering algorithm (OCA)-based RBF network. In this present system, we propose a completely unsupervised clustering algorithm for training of the RBF network in which the system automatically searches for suitable threshold to perform natural clustering. This system performs the identity of a person irrespective of different facial expressions, poses, and partial occlusions. Experimental results show that the performance of the system in terms of accuracy, precision, recall, and F-score is moderately high. At the same time, the total learning time as well as performance evaluation time is moderately low.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yang, M.H., Kriegman, D.J., Ahuja, N.: Detecting faces in images: a survey. IEEE Trans. Pattern Anal. Mach. intell. 24(1), 34–58 (2002)
Sarker, G.: An unsupervised natural clustering with optimal conceptual affinity. J. Intell. Syst. 19(3), 289–300 (2010)
Sarker, G., Roy, K.: A modified RBF network with optimal clustering for face identification and localization. Int. J. Adv. Comput. Eng. Networking 1(3), 30–35 (2013)
Bhakta, D., Sarker, G.: A radial basis function network for face identification and subsequent localization. In: International Conference on Computer Science and Information Technology (ICCSIT), pp. 1–6 (2013)
Sarker, G.: An optimal back propagation network for face identification and localization. Int. J. Comput. Appl. (IJCA), ACTA Press, 35(2) (2013)
Wu, H., Chen, Q., Yachida, M.: Face detection from color images using fuzzy pattern matching method. IEEE Trans. Pattern Anal. Mach. Intell. 21(6) (1999)
Moody, J., Draken, C.J.: Fast learning in network of locally tuned processing units. Neural Comput. 1, 281–294 (1989)
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 1–18 (2009)
Ali, S.: Novel fast and efficient face recognition technique. Int. J. IT Eng. Appl. Sci. Res. (IJIEASR) 1(1), 5–9 (2012)
Gao, W.C.Y.: Recognizing partially occluded faces from a single sample per class using string-based matching LNCS 6313, pp. 496–509. Springer, Berlin (2010)
Marsico, M.D., Nappi, M., Riccio, D.: FARO: Face recognition against occlusions and expression variations. IEEE Trans. Syst. Man Cybern.—Part A: Syst. Humans 40(1), 121–132 (2010)
Pudi, V., Radhakrishna, P.: Data Mining. Oxford Press, India (2009)
Thomaz, C.E., Giraldi, G.A.: A new ranking method for principal components analysis and its application to face image analysis. Image Vis. Comput. 28(6), 902–913 (2010)
Bhakta, D., Sarker, G.: A rotation and location invariant face identification and localization with or without occlusion using modified RBFN. In: IEEE 2nd International Conference on Image Information Processing (ICIIP-2013), pp. 533–538
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer India
About this paper
Cite this paper
Bhakta, D., Sarker, G. (2015). An Unsupervised OCA-based RBFN for Clear and Occluded Face Identification. In: Mandal, D., Kar, R., Das, S., Panigrahi, B. (eds) Intelligent Computing and Applications. Advances in Intelligent Systems and Computing, vol 343. Springer, New Delhi. https://doi.org/10.1007/978-81-322-2268-2_3
Download citation
DOI: https://doi.org/10.1007/978-81-322-2268-2_3
Published:
Publisher Name: Springer, New Delhi
Print ISBN: 978-81-322-2267-5
Online ISBN: 978-81-322-2268-2
eBook Packages: EngineeringEngineering (R0)