L1-L1 norms for face super-resolution with mixed Gaussian-impulse noise

In real world surveillance application, the captured faces are often low resolution (LR) and corrupted by mixed Gaussian-impulse noise during the acquisition and transmission processes. In this paper, we propose an effective patch-based face super-resolution method to reconstruct a high resolution (HR) face image given an LR observation that is corrupted by mixed Gaussian-impulse noise. To represent the corrupted image patches, a sparse regularization combined with an l\ data fitting term is proposed. In the proposed model, both the patch reconstruction term and the regularization term are in the l\ norm form. As a result, the model is called norms. In addition, since image pixels have nonnegative intensities, we further add a nonnegative constraint to the patch representation model. Experimental results demonstrate that the proposed norms based method can achieve superior face super-resolution performance over several state-of-the-art approaches based on the objective results in terms of P-SNR, as well as the visual perceptual quality.

[1]  Harry Shum,et al.  A two-step approach to hallucinating faces: global parametric model and local nonparametric model , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Jian Yang,et al.  Mixed Noise Removal by Weighted Encoding With Sparse Nonlocal Regularization , 2014, IEEE Transactions on Image Processing.

[3]  Ming Yan,et al.  Restoration of Images Corrupted by Impulse Noise and Mixed Gaussian Impulse Noise using Blind Inpainting , 2013, SIAM J. Imaging Sci..

[4]  Andrew Zisserman,et al.  Super-resolution from multiple views using learnt image models , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Ruimin Hu,et al.  Noise Robust Face Hallucination via Locality-Constrained Representation , 2014, IEEE Transactions on Multimedia.

[6]  Hongbin Zha,et al.  Structure-Sensitive Superpixels via Geodesic Distance , 2011, 2011 International Conference on Computer Vision.

[7]  Yuning Jiang,et al.  Learning Face Hallucination in the Wild , 2015, AAAI.

[8]  Ruimin Hu,et al.  Facial Image Hallucination Through Coupled-Layer Neighbor Embedding , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Ruimin Hu,et al.  Position-Patch Based Face Hallucination via Locality-Constrained Representation , 2012, 2012 IEEE International Conference on Multimedia and Expo.

[10]  Chun Qi,et al.  Hallucinating face by position-patch , 2010, Pattern Recognit..

[11]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..

[12]  Takeo Kanade,et al.  Hallucinating faces , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[13]  C. Thomaz,et al.  A new ranking method for principal components analysis and its application to face image analysis , 2010, Image Vis. Comput..

[14]  Karl Kunisch,et al.  Denoising of Smooth Images Using L1-Fitting , 2005, Computing.

[15]  Maoguo Gong,et al.  Position-Patch Based Face Hallucination Using Convex Optimization , 2011, IEEE Signal Processing Letters.

[16]  Wilfried Philips,et al.  Sparse representation and position prior based face hallucination upon classified over-complete dictionaries , 2012, Signal Process..

[17]  Zhiliang Zhu,et al.  Fast Single Image Super-Resolution via Self-Example Learning and Sparse Representation , 2014, IEEE Transactions on Multimedia.

[18]  Yuan Yan Tang,et al.  Weighted Couple Sparse Representation With Classified Regularization for Impulse Noise Removal , 2015, IEEE Transactions on Image Processing.

[19]  Wai-kuen Cham,et al.  Hallucinating Face in the DCT Domain , 2011, IEEE Transactions on Image Processing.

[20]  Mila Nikolova,et al.  Minimizers of Cost-Functions Involving Nonsmooth Data-Fidelity Terms. Application to the Processing of Outliers , 2002, SIAM J. Numer. Anal..

[21]  Xiaogang Wang,et al.  Hallucinating face by eigentransformation , 2005, IEEE Trans. Syst. Man Cybern. Part C.

[22]  Zhuowen Tu,et al.  Robust Point Matching via Vector Field Consensus , 2014, IEEE Transactions on Image Processing.

[23]  Ruimin Hu,et al.  Locality-constraint iterative neighbor embedding for face hallucination , 2013, 2013 IEEE International Conference on Multimedia and Expo (ICME).

[24]  Junjun Jiang,et al.  Robust Feature Matching for Remote Sensing Image Registration via Locally Linear Transforming , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Yicong Zhou,et al.  A new weighted mean filter with a two-phase detector for removing impulse noise , 2015, Inf. Sci..

[26]  Alan L. Yuille,et al.  Non-Rigid Point Set Registration by Preserving Global and Local Structures , 2016, IEEE Transactions on Image Processing.

[27]  Shiguang Shan,et al.  Aligning Coupled Manifolds for Face Hallucination , 2009, IEEE Signal Processing Letters.

[28]  Thomas S. Huang,et al.  Face hallucination VIA sparse coding , 2008, 2008 15th IEEE International Conference on Image Processing.

[29]  Reuben A. Farrugia,et al.  Face Hallucination Using Linear Models of Coupled Sparse Support , 2015, IEEE Transactions on Image Processing.

[30]  Ruimin Hu,et al.  CDMMA: Coupled discriminant multi-manifold analysis for matching low-resolution face images , 2016, Signal Process..

[31]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[32]  Chen Chen,et al.  Single-image super-resolution using multihypothesis prediction , 2012, 2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).

[33]  Christos-Savvas Bouganis,et al.  Robust multi-image based blind face hallucination , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Jian Yang,et al.  A novel sparse representation based framework for face image super-resolution , 2014, Neurocomputing.

[35]  Liang Chen,et al.  Coupled Discriminant Multi-Manifold Analysis with Application to Low-Resolution Face Recognition , 2015, MMM.

[36]  D. Yeung,et al.  Super-resolution through neighbor embedding , 2004, CVPR 2004.

[37]  Shaogang Gong,et al.  Generalized Face Super-Resolution , 2008, IEEE Transactions on Image Processing.

[38]  Xuelong Li,et al.  A Comprehensive Survey to Face Hallucination , 2013, International Journal of Computer Vision.

[39]  Ruimin Hu,et al.  Face Super-Resolution via Multilayer Locality-Constrained Iterative Neighbor Embedding and Intermediate Dictionary Learning , 2014, IEEE Transactions on Image Processing.

[40]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[41]  Zhuowen Tu,et al.  Robust $L_{2}E$ Estimation of Transformation for Non-Rigid Registration , 2015, IEEE Transactions on Signal Processing.