Abstract
A novel face hallucination method is proposed in this paper for the reconstruction of a high-resolution face image from Sparse Representation. By joint training two dictionaries for the low-and high-resolution image patches, the method efficiently builds sparse association between high-frequency components of HR image patches and LR image feature patches, and defines the association as a prior knowledge, Using MAP criteria to guide super-resolution reconstruction with respect to their own dictionaries. The learned Dictionary pair is a more compact representation of the patch pairs, reducing the computational cost substantially. Experiments show that the proposed method generates higher-quality images and costs less computational time than some recent face image super-resolution (hallucination) techniques, and achieves much better results than many state-of-the-art algorithms in terms of both PSNR and visual perception.
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.
Similar content being viewed by others
References
Baker, S., Kanade, T.: Hallucinating faces. In: Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France, pp. 83–88 (2000)
Baker, S., Kanade, T.: Limits on super-resolution and how to break them. IEEE Trans. Pattern Anal. Mach. Intell. 24(9), 1167–1183 (2002)
Freeman, W.T., Pasztor, E.C.: Learning low-level vision. In: Proc. ICCV 1999, Kerkyra, Greece, pp. 1182–1189 (1999)
Freeman, W.T., Jones, T.R., Pasztor, E.C.: Example-based super resolution. IEEE Computer Graphics and Applications 22(2), 56–65 (2002)
Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Sales, D.H.: Image analogies. In: Proceedings of SIGGRAPH 2001, Los Angeles, California, pp. 327–340 (2001)
Liu, C., Shum, H.Y., Zhang, C.S.: A two-step approach to hallucinating faces: global parametric model and local nonparametric model. In: Proceedings of CVPR 2001, Kauai Marriott, Hawaii, pp. 192–198 (2001)
Sun, J., Zheng, N.N., Tao, H., Shum, H.Y.: Image hallucination with primal sketch priors. In: Proceedings of CVPR 2003, Madison, Wisconsin, pp. 729–736 (2003)
Lee, C., Eden, M., Unser, M.: High-quality image resizing using oblique projection operators. IEEE Trans. Image Process. 7(5), 679–692 (1998)
Li, M., Cheng, J., Le, X., Luo, H.-M.: Super-resolution Reconstruction Based on Improved Sparse Codin. J. Opto-Electronic Engineering 38(1), 127–133 (2011)
Mairal, J., Sapiro, G., Elad, M.: Learning multiscale sparse representations for image and video restoration. J. SIAM Multiscale Modeling and Simulation 7(1), 214–241 (2008)
Li, X., Orchard, M.T.: New edge-directed interpolation. IEEE Trans. Image Process. 10(10), 1521–1527 (2001)
Yang, J.C., Wright, J., Huang, T., et al.: Image Super-Resolution via Sparse Representation. IEEE Trans. Image Processing 19(11), 2861–2873 (2010)
Phillips, P.J., Moon, H., Rizvi, S., Rauss, P.J.: The FERET evaluation methodology for facere cognition algorithms. IEEE Trans. Pattern Anal. 22(10), 1090–1104 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cuihong, X., Ming, Y., Chao, J., Gang, Y. (2011). Hallucinating Face by Sparse Representation. In: Tan, H. (eds) Informatics in Control, Automation and Robotics. Lecture Notes in Electrical Engineering, vol 132. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25899-2_109
Download citation
DOI: https://doi.org/10.1007/978-3-642-25899-2_109
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25898-5
Online ISBN: 978-3-642-25899-2
eBook Packages: EngineeringEngineering (R0)