A novel tensor framework for face hallucination
Keywords:Tensor Regression Analysis, face hallucination, super-resolution
Normal regression analysis methods can be used to find a relationship between high-resolution (HR) and low-resolution (LR) features. Previous work neglected to use regression analysis methods in finding a relationship between the error of face reconstruction and the LR feature in tensor objects. Because of this limitation, the image as a featured matrix is transformed into one-dimensional vectors, causing a loss of spatial information. By using our method this problem is eliminated. In our proposal we have developed a new face hallucination framework, using a Tensor Regression Analysis (TRA) to further enhance the quality of an image. Error estimation of in the validation system providing the correct final result is further applied into our framework through regression analysis. In doing this, we present our framework based on a two-tier approach. First a global step and second a local step. In the global step, we apply the TRA in order to find a relationship between the features of LR and HR based on multilinear Principal Component Analysis (PCA). The regression coefficients are acquired through the relationship between featured HR and LR. In the local step, the TRA is used to find the relationship between the LR features and the error of validation process, obtained from the global step. Experimental results obtained from a well-known face database show that the resolution and quality of the hallucinated face images obtained with our proposed method are greatly enhanced and improved in comparison with the traditional methods used.
Baker, S., & Kanade, T. (2002). Limits on super-resolution and how to break them. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 1167-1183.
Elad, M., & Feuer, A. (1997). Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images. In IEEE Transactions on Image Processing, 6, 1646-1658.
Farsiu, S, Elad, M., & Milanfar, P. (2006) Multiframe demosaicing and super-resolution of color images. In IEEE Transactions on Image Processing, 15, 141-159.
Freeman, W. T., & Pasztor, E. C. (1999). Learning low-level vision. In 7th IEEE International Conference on Computer Vision, 1182-1189.
Hardie, R. C., Barnard, K. J., & Armstrong E. E. (1997). Joint MAP, registration and high-resolution image estimation using a sequence of undersampled images. In IEEE Transactions on Image Processing, 6, 1621-1633.
Hsieh, H., & Andrews, H. (1978). Cubic splines for image interpolation and digital filtering. In IEEE Transactions on Acoustics, Speech and Signal Processing, 26, 508-517.
Hua, S., & Shutao, L. (2009). Hallucinating faces by interpolation and principal component analysis. In Second International Symposium on Computational Intelligence and Design (ISCID), 295-298.
Jian, S., Zongben, X. & Heung-Yeung, S. (2008). Image super-resolution using gradient profile prior.In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1-8.
Liu, C., Shum, H-Y., & Zhang, C-S. (2001). A two-step approach to hallucinating faces: Global parametric model and local nonparametric model.In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 1, 192-198, 2001.
Kimmel, R. (1999). Demosaicing: image reconstruction from color CCD samples. In IEEE Transactions on Image Processing, 8, 1221-1228.
Kumar, B. G. V., & Aravind, R. (2008). A 2D model for face superresolution. In 19th IEEE Conferences, 1-4. DOI: 10.1109/ICPR.2008.4761072
Liu, C., Shum, H.-Y., & Freeman, W. (2007). Face hallucination: Theory and practice." International Journal of Computer Vision, 75, 115-134.
Liu, W., Lin, D., & Tang, X. (2005). Neighbor combination and transformation for hallucinating faces. In IEEE International Conference on Multimedia and Expo (ICME), 1-4.
McHugh, S. (n.d.). Digital Image Interpolation. [On line] Retrieved 15 March 2011 from http://www.cambridgeincolour.com/tutorials/image-interpolation.htm
Nuno-Maganda, M. A., & Arias-Estrada, M. O. (2005). Real-time FPGA-based Architecture for bicubic interpolation: An application for digital image scaling. In International Conference on Reconfigurable Computing and FPGAs (ReConFig), 1-8.
Park, J-S., & Lee, S-W. (2008). An example-based face hallucination method for Single-frame, low-resolution facial images. In IEEE Transactions on Image Processing, 17, 1806-1816.
Park, S. C., Park, M. K., & Kang M. G. (2003) Super-Resolution Image Reconstruction. In IEEE Signal Processing Magazine,Vol, 21-36.
Senjian, A., Wanquan, L. & Venkatesh, S. (2007). Face recognition using kernel ridge regression. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1-7.
Wang, X., & Tang, X. (2005). Hallucinating face by eigentransformation. In IEEE Transactions on Systems, Man and Cybernetics, 35, 425-434.
Wei, L., Dahua, L., & Xiaoou, T. (2005). Hallucinating faces: Tensor patch super-resolution and coupled residue compensation. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 478-484.
Wikipedia. (n.d.). Bicubic Interpolation.[On line] Retrieved 15 March 2011from: http://en.wikipedia.org/wiki/Bicubic_interpolation
Xin, L., & Orchard, M. T. (2001). New edge-directed interpolation. In IEEE Transactions on Image Processing, 10, 1521-1527.
Yang Jianchao, Wright John, Huang Thomas S. & Ma Yi. "Image Super-Resolution Via Sparse Representation." IEEE Transactions on Image Processing. 19 (2010): 2861-2873.
Zhang, X-g. ( 2008). A new kind of super-resolution reconstruction Algorithm based on the ICM and the constrained cubic spline interpolation.In International Symposium on Intelligent Information Technology Application Workshops, 530-534.
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.