Abstract
This paper proposes a method for reconstructing a whole face image from partial information based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information of pixels in an given region, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture. In such an over-determined condition, where the number of pixels in the given region is greater than the number of prototypes, we find an optimal solution using projection for least square minimization(LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos. We interpret the encouraging performance of our proposed method as evidence in support of the hypothesis that the human visual system may reconstruct an whole information from partial information using prototypical examples.
This research was supported by Creative Research Initiatives of the Ministry of Science and Technology, Korea.
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
Beymer, D., Shashua, A. and Poggio, T.: Example-based image analysis and synthesis. AI Memo 1431/CBCL Paper 80, Massachusetts Institute of Technology, Cambridge, MA, November (1993)
Beymer, D., Poggio, T.: Image representation for visual learning. Science 272 (1996) 1905–1909
Blanz, V., Vetter, T.: Morphable model for the synthesis of 3D faces. Proc. of SIGGRAPH’99, Los Angeles, (1999) 187–194
Hwang, B.-W., Blanz, V., Vetter, T., Lee, S.-W.: Face reconstruction from a small number of feature points. Proc. of Int. Conf. on Pattern Recognition 2, Barcelona, September (2000) 842–845 Jones, M. J., Poggio, T.: Hierarchical morphable models. Proc. of Computer Vision and Pattern Recognition, Santa Barbara (1998) 820-826
Jones, M. J., Sinha, P., Vetter, T., Poggio, T.: Top-down learning of low-level vision tasks[brief communication]. Current Biology 7 (1997) 991–994
Jones, M. J., Poggio, T.: Multidimensional morphable models: a framework for representing and matching object classes. Jornal of Computer Vision 29 2 (1998) 107–131
Narendra, P. M.: A Separable median filter for image noise smoothing. IEEE Trans. on Pattern Analysis and Machine Intelligence 3 1 (1981) 20–29
Poggio, T., Vetter, T.: Recognition and structure from one 2D model view: observations on prototypes, object classes and symmetries. AI Memo 1347/CBIP Paper 69, Massachusetts Institute of Technology, Cambridge, MA, February (1992)
Strang, G.: Linear algebra and its applications. Harcourt Brace Jovanovich College publishers, Orlando, FL, (1988) 442–451
Turk M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience 3 1 (1991) 71–86
Vetter T., Troje, N. E.: Separation of texture and shape in images of faces for image coding and synthesis. Journal of the Optical Society of America A 14 9 (1997) 2152–2161
Windyga, P. S.: Fast impulsive noise removal. IEEE Trans. on Image Processing 10 1 (2001) 173–178
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hwang, BW., Lee, SW. (2002). Face Reconstruction from Partial Information Based on a Morphable Face Model. In: Bülthoff, H.H., Wallraven, C., Lee, SW., Poggio, T.A. (eds) Biologically Motivated Computer Vision. BMCV 2002. Lecture Notes in Computer Science, vol 2525. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36181-2_50
Download citation
DOI: https://doi.org/10.1007/3-540-36181-2_50
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00174-4
Online ISBN: 978-3-540-36181-7
eBook Packages: Springer Book Archive