Abstract
Face recognition systems robust to major occlusions have wide applications ranging from consumer products with biometric features to surveillance and law enforcement applications. In unconstrained scenarios, faces are often subject to occlusions, apart from common variations such as pose, illumination, scale, orientation and so on. In this paper we propose a novel Bayesian oriented occlusion model inspired by psychophysical mechanisms to recognize faces prone to occlusions amidst other common variations. We have discovered and modeled similarity maps that exist in facial domains by means of Bayesian Networks. The proposed model is capable of efficiently learning and exploiting these maps from the facial domain. Hence it can tackle the occlusion uncertainty reasonably well. Improved recognition rates over state of the art techniques have been observed.
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
Preview
Unable to display preview. Download preview PDF.
References
Martinez, A.M.: Recognizing imprecisely localized, partially occluded and expression variant faces from a single sample per class. IEEE Trans. Pattern Analysis and Machine Intelligence 24(6), 748–763 (2002)
Kim, J., Choi, J., Yi, J., Turk, M.: Effective representation using ICA for face recognition robust to local distortion and partial occlusion. IEEE Trans. Pattern Analysis and Machine Intelligence 27(12), 1977–1981 (2005)
Kanan, H.R., Faez, K.: Recognizing faces using Adaptively Weighted Sub-Gabor Array from a single sample image per enrolled subject. Image & Vision Computing 28(3), 438–448 (2010)
Solan, Z., Ruppin, E.: Similarity in perception: A window to brain organization. Journal of Cognitive Neuroscience 13, 18–30 (1999)
Nosofsky, R.M., Zaki, S.R.: A hybrid-similarity exemplar model for predicting distinctiveness effects in perceptual oldnew recognition. Journal of Experimental Psychology: Learning, Memory, and Cognition 29, 1194–1209 (2003)
Solar, J.R., Navarrete, P.: Eigenspace-based Face Recognition. Springer Engineering Series (2001)
Tversky, A.: Features of similarity. Psychological Review 84, 327–352 (1977)
Rakover, S.S.: Featural vs. configurational information in faces: A conceptual and empirical analysis. British Journal of Psychology 93, 1–30 (2002)
Bartlett, M.S., Movellan, J.R.: Face recognition by independent component analysis. IEEE Trans. on Neural Networks 13(6), 1450–1464 (2002)
Fific, A.: Emerging holistic properties at face value: assessing characteristics of face perception, Ph.D. thesis (2005)
Schwaninger, A., Wallraven, C., Bulthoff, H.H.: Computational modeling of face recognition based on psychophysical experiments. Swiss Journal of Psychology 63(3), 207–215 (2004)
Behrmann, M., Zemel, R.S., Mozer, M.C.: Object-based attention and occlusion. Journal of Experimental Psychology: Human Perception and Performance 24(4), 1011–1036 (1998)
Dakin, S.C., Watt, R.J.: Biological bar codes in human faces. Journal of Vision 9(4), 1–10 (2009)
Jensen, F.V., Nielsen, T.D.: Bayesian Networks and Decision Graphs. Springer, Heidelberg (2007)
Martinez, A.M., Benavente, R.: The AR Face Database. CVC technical report no. 24, Tech. rep. (1998)
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
Venkat, I., Khader, A.T., Subramanian, K.G., De Wilde, P. (2011). Psychophysically Inspired Bayesian Occlusion Model to Recognize Occluded Faces. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds) Computer Analysis of Images and Patterns. CAIP 2011. Lecture Notes in Computer Science, vol 6854. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23672-3_51
Download citation
DOI: https://doi.org/10.1007/978-3-642-23672-3_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23671-6
Online ISBN: 978-3-642-23672-3
eBook Packages: Computer ScienceComputer Science (R0)