Image Super-Resolution Algorithm Based on an Improved Sparse Autoencoder

Due to the limitations of the resolution of the imaging system and the influence of scene changes and other factors, sometimes only low-resolution images can be acquired, which cannot satisfy the practical application’s requirements. To improve the quality of low-resolution images, a novel super-resolution algorithm based on an improved sparse autoencoder is proposed. Firstly, in the training set preprocessing stage, the high- and low-resolution image training sets are constructed, respectively, by using high-frequency information of the training samples as the characterization, and then the zero-phase component analysis whitening technique is utilized to decorrelate the formed joint training set to reduce its redundancy. Secondly, a constructed sparse regularization term is added to the cost function of the traditional sparse autoencoder to further strengthen the sparseness constraint on the hidden layer. Finally, in the dictionary learning stage, the improved sparse autoencoder is adopted to achieve unsupervised dictionary learning to improve the accuracy and stability of the dictionary. Experimental results validate that the proposed algorithm outperforms the existing algorithms both in terms of the subjective visual perception and the objective evaluation indices, including the peak signal-to-noise ratio and the structural similarity measure.

[1]  Xiao-Yuan Jing,et al.  Super-resolution Person re-identification with semi-coupled low-rank discriminant dictionary learning , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Hu Yue,et al.  Research of Definition Assessment based on No-reference Digital Image Quality , 2011 .

[3]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[4]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[5]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

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

[7]  Xiaofeng Li,et al.  Single Image Super-Resolution Based on the Feature Sign Method , 2015 .

[8]  D. Donoho For most large underdetermined systems of equations, the minimal 𝓁1‐norm near‐solution approximates the sparsest near‐solution , 2006 .

[9]  Xiu Zhang,et al.  Image super-resolution reconstruction based on fusion of K-SVD and semi-coupled dictionary learning , 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

[10]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[11]  Chang-Hwan Son,et al.  Local Learned Dictionaries Optimized to Edge Orientation for Inverse Halftoning , 2014, IEEE Transactions on Image Processing.

[12]  Yijun Liu,et al.  Single image super-resolution reconstruction method based on LC-KSVD algorithm , 2017 .

[13]  Fu Yao,et al.  Image quality evaluation based on image weighted separating block peak signal to noise ratio , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[14]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[15]  Min-Sung Koh,et al.  Turbo inpainting: Iterative K-SVD with a new dictionary , 2009, 2009 IEEE International Workshop on Multimedia Signal Processing.

[16]  Youfu Li,et al.  Feature extraction based on Lp-norm generalized principal component analysis , 2013, Pattern Recognit. Lett..

[17]  Michael Elad,et al.  Sparse Representation for Color Image Restoration , 2008, IEEE Transactions on Image Processing.

[18]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[19]  Dattatray V. Jadhav,et al.  Feature extraction using Radon and wavelet transforms with application to face recognition , 2009, Neurocomputing.

[20]  Angshul Majumdar,et al.  Deep Dictionary Learning vs Deep Belief Network vs Stacked Autoencoder: An Empirical Analysis , 2016, ICONIP.

[21]  Xia De-sheng Research of Measurement for Digital Image Definition , 2004 .

[22]  Daniel Rueckert,et al.  Dictionary Learning and Time Sparsity for Dynamic MR Data Reconstruction , 2014, IEEE Transactions on Medical Imaging.

[23]  Aline Roumy,et al.  Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding , 2012, BMVC.

[24]  Luc Van Gool,et al.  A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution , 2014, ACCV.

[25]  Guillermo Sapiro,et al.  Online Learning for Matrix Factorization and Sparse Coding , 2009, J. Mach. Learn. Res..

[26]  Kjersti Engan,et al.  Frame based signal compression using method of optimal directions (MOD) , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[27]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

[28]  Hui Huang,et al.  Application of regularization technique in image super-resolution algorithm via sparse representation , 2017, Optoelectronics Letters.

[29]  Pan Zong-x Single Image Super Resolution Based on Adaptive Multi-Dictionary Learning , 2015 .

[30]  Detian Huang,et al.  Image super-resolution reconstruction based on regularization technique and guided filter , 2017 .

[31]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[32]  Ali Aghagolzadeh,et al.  Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology , 2010, Pattern Recognit..

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

[34]  Rabab Kreidieh Ward,et al.  Learning space-time dictionaries for blind compressed sensing dynamic MRI reconstruction , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[35]  Luc Van Gool,et al.  Anchored Neighborhood Regression for Fast Example-Based Super-Resolution , 2013, 2013 IEEE International Conference on Computer Vision.

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