Abstract
This paper presents an approach for realistic virtual view generation using appearance clustering based local view transition model, with its target application on cross-pose face recognition. Previously, the traditional global pattern based view transition modelĀ (VTM) method was extended to its local version called LVTM, which learns the linear transformation of pixel values between frontal and non-frontal image pairs using partial image in a small region for each location, rather than transforming the entire image pattern. In this paper, we show that the accuracy of the appearance transition model and the recognition rate can be further improved by better exploiting the inherent linear relationship between frontal-nonfrontal face image patch pairs. For each specific location, instead of learning a common transformation as in the LVTM, the corresponding local patches are first clustered based on appearance similarity distance metric and then the transition models are learned separately for each cluster. In the testing stage, each local patch for the input non-frontal probe image is transformed using the learned local view transition model corresponding to the most visually similar cluster. The experimental results on a real-world face dataset demonstrated the superiority of the proposed method in terms of recognition rate.
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
Zhao, W., Chellappa, R., Philips, P.J., Rosenfeld, A.: Face recognition: A literature survey. ACM Computer SurveyĀ 35(4), 399ā459 (2003)
Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: Proc. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586ā591 (1991)
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine IntelligenceĀ 19(7), 711ā720 (1997)
Blanz, V.G., Phillips, P.J., Vetter, T.: Face recognition based on frontal views generated from non-frontal images. In: Proc. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 454ā461 (2005)
Beymer, D.: Face recognition under varying pose. In: Proc. 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 756ā761 (1994)
Utsumi, A., Tetsutani, N.: Adaptation of appearance model for human tracking using geometrical pixel value distribution. In: Proc. 6th Asian Conference on Computer Vision, pp. 794ā799 (2004)
Kono, Y., Takahashi, T., Deguchi, D., Ide, I., Murase, H.: Frontal Face Generation from Multiple Low-Resolution Non-frontal Faces for Face Recognition. In: Koch, R., Huang, F. (eds.) ACCV 2010 Workshops, Part I. LNCS, vol.Ā 6468, pp. 175ā183. Springer, Heidelberg (2011)
Baker, S., Kanade, T.: Hallucinating faces. In: Proc. 2000 IEEE Conference on Automatic Face and Gesture Recognition, pp. 83ā88 (2000)
Chai, X., Shan, S., Chen, X., Gao, W.: Locally linear regression for pose-invariant face recognition. IEEE Transactions on Image ProcessingĀ 16(7), 1716ā1725 (2007)
Beymer, D., Poggio, T.: Face recognition from one example view. In: Proc. 5th International Conference on Computer Vision, pp. 500ā507 (1995)
Goesele, M., Curless, B., Seitz, S.M.: Multi-view stereo revisited. In: Proc. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2402ā2409 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, X., Takahashi, T., Deguchi, D., Ide, I., Murase, H. (2013). Virtual View Generation Using Clustering Based Local View Transition Model. In: Park, JI., Kim, J. (eds) Computer Vision - ACCV 2012 Workshops. ACCV 2012. Lecture Notes in Computer Science, vol 7729. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37484-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-37484-5_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37483-8
Online ISBN: 978-3-642-37484-5
eBook Packages: Computer ScienceComputer Science (R0)