Super-Resolution of Face Images Using Weighted Elastic Net Constrained Sparse Representation

High-resolution (HR) face images are usually preferred in many computer vision tasks. However, low-resolution (LR) face images, which are often obtained in real scenarios, can be converted to a high resolution with the super-resolution techniques. In this paper, we propose the weighted elastic net constrained sparse representation (WENSR) super resolution method for face images. The method considers image gradient and weighted elastic net penalties. Due to the high similarity between human faces, it is not very suitable to only use ${\ell 1}$ -norm in the sparse representation model. The elastic net has a grouping effect and is more suitable for real-world data. The gradient is very important information in the image, we also use image gradient to enhance the final output. The tests of our method on both synthetic data and real-world data, such as FEI, CAS-PEAL-R1, and CMU+MIT face image dataset suggest a competitive performance gain in terms of peak signal to noise ratio (PSNR) and structural similarity (SSIM).

[1]  Truong Q. Nguyen,et al.  Single Image Superresolution Based on Support Vector Regression , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[2]  Michael Elad,et al.  Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images , 1997, IEEE Trans. Image Process..

[3]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[4]  Chun Qi,et al.  Position-based face hallucination method , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[5]  William T. Freeman,et al.  Learning low-level vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[7]  Wen Gao,et al.  The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations , 2008, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[8]  Lei Zhang,et al.  An edge-guided image interpolation algorithm via directional filtering and data fusion , 2006, IEEE Transactions on Image Processing.

[9]  Y. Zhang,et al.  Augmented Lagrangian alternating direction method for matrix separation based on low-rank factorization , 2014, Optim. Methods Softw..

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

[11]  H Stark,et al.  High-resolution image recovery from image-plane arrays, using convex projections. , 1989, Journal of the Optical Society of America. A, Optics and image science.

[12]  Xiaobing Pei,et al.  Face Hallucination via Gradient Constrained Sparse Representation , 2018, IEEE Access.

[13]  Seong-Whan Lee,et al.  An Example-Based Face Hallucination Method for Single-Frame, Low-Resolution Facial Images , 2008, IEEE Transactions on Image Processing.

[14]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[15]  Takeo Kanade,et al.  Limits on super-resolution and how to break them , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[16]  Alan L. Yuille,et al.  Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples , 2016, IEEE Transactions on Image Processing.

[17]  Horst Bischof,et al.  Multiple Object Tracking Using Local PCA , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

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

[19]  D. Donoho.  For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution , 2006 .

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

[21]  Thomas S. Huang,et al.  Coupled Dictionary Training for Image Super-Resolution , 2012, IEEE Transactions on Image Processing.

[22]  Wai-kuen Cham,et al.  Learning-based face hallucination in DCT domain , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Yi Chai,et al.  A novel multi-modality image fusion method based on image decomposition and sparse representation , 2017, Inf. Sci..

[24]  Michael Elad,et al.  From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images , 2009, SIAM Rev..

[25]  Zheng Wang,et al.  SRLSP: A Face Image Super-Resolution Algorithm Using Smooth Regression With Local Structure Prior , 2017, IEEE Transactions on Multimedia.

[26]  Michal Irani,et al.  Improving resolution by image registration , 1991, CVGIP Graph. Model. Image Process..

[27]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

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

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

[30]  Lorenzo Rosasco,et al.  Elastic-net regularization in learning theory , 2008, J. Complex..

[31]  Junping Zhang,et al.  Super-resolution of human face image using canonical correlation analysis , 2010, Pattern Recognit..

[32]  Rama Chellappa,et al.  Super-Resolution of Face Images Using Kernel PCA-Based Prior , 2007, IEEE Transactions on Multimedia.

[33]  Jing Yu,et al.  Projection onto convex sets super-resolution image reconstruction based on wavelet bi-cubic interpolation , 2011, Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology.

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

[35]  Xuesong Zhang,et al.  An adaptive learning method for face hallucination using Locality Preserving Projections , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[36]  Harry Shum,et al.  Face Hallucination: Theory and Practice , 2007, International Journal of Computer Vision.

[37]  Daniel P. Robinson,et al.  A Flexible ADMM Algorithm for Big Data Applications , 2015, J. Sci. Comput..

[38]  Shaopeng Wang,et al.  A Simple Approach to Multiview Face Hallucination , 2010, IEEE Signal Processing Letters.

[39]  Di Wang,et al.  A Phase Congruency and Local Laplacian Energy Based Multi-Modality Medical Image Fusion Method in NSCT Domain , 2019, IEEE Access.

[40]  Hsieh Hou,et al.  Cubic splines for image interpolation and digital filtering , 1978 .

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

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

[43]  Lei Zhang,et al.  Nonlocal back-projection for adaptive image enlargement , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

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

[45]  Zhengtao Yu,et al.  Fractional differential and variational method for image fusion and super-resolution , 2016, Neurocomputing.

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

[47]  Zhi-Quan Luo,et al.  On the linear convergence of the alternating direction method of multipliers , 2012, Mathematical Programming.