Super-resolution restoration of MMW image based on sparse representation method

Abstract This paper presents a new super-resolution (SR) restoration method of a single millimeter wave image (MMW), based on sparse single representation. A single MMW image is in fact a low-resolution one that is viewed as a downsampled version of a high-resolution image, whose image patches are assumed to be well represented as a sparse linear combination of elements from an appropriately chosen overcomplete dictionary. The theoretical results from compressed sensing ensure that under mild conditions, the sparse representation can be correctly restored from the downsampled signal. Inspired by this idea, a sparse representation for each image path of the MMW image with hardly low-resolution is sought, and then the coefficients of this sparse representation are used to generate the high-resolution output. The high- and low-resolution dictionary pair can be obtained by utilizing the modified fast sparse coding (FSC) algorithm, and it is a more compact representation of the image patch pairs, which hardly reduces the computational cost. In tests, image patches of several high-resolution natural images with different classes and their corresponding low-resolution versions are firstly used to train the dictionary pair. Further, utilizing the learned dictionary pair, the MMW image is restored efficiently. For the restored natural images, the image quality is measured by single noise ratio (SNR), while for the MMW image, it is not suitable to use the SNR criterion because much noise existed in the MMW image. So, the restored MMW image’s quality is measured by the relative SNR (RSNR). Compared with other SR restoration methods of bicubic, Lucy–Richardson (L–R) and neighbor embedding (NE), the simulation experimental results testify that the sparse representation is indeed effective in the super-resolution restoration task of the MMW image.

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

[2]  Tony F. Chan,et al.  Image processing and analysis - variational, PDE, wavelet, and stochastic methods , 2005 .

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

[4]  Hong Yan,et al.  A POCS-based constrained total least squares algorithm for image restoration , 2006, J. Vis. Commun. Image Represent..

[5]  Lu Xuan-min.  POCS Super-resolution Image Reconstruction Based on Improved PSF , 2011 .

[6]  C. Matzler,et al.  Stereoscopic passive millimeter-wave imaging and ranging , 2005, IEEE Transactions on Microwave Theory and Techniques.

[7]  Xavier Binefa,et al.  Concealed object detection and segmentation over millimetric waves images , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[8]  Zheng Xin.  Research on Passive Millimeter Wave Image Super-Resolution Algorithm and Real-time Implementation , 2009 .

[9]  Wei Jia,et al.  Robust Classification Method of Tumor Subtype by Using Correlation Filters , 2012, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[10]  Guo Wei.  A MATHEMATICAL MORPHOLOGICAL FOR EDGE DETECTION IN MILLIMETER WAVE RADIOMETRIC IMAGES , 2006 .

[11]  Gan Xin.  Super-resolution Reconstruction Method of Passive Millimeter-wave Image , 2009 .

[12]  D. A. Fish,et al.  Blind deconvolution by means of the Richardson-Lucy algorithm. , 1995 .

[13]  Chao Wang,et al.  Supervised feature extraction based on orthogonal discriminant projection , 2009, Neurocomputing.

[14]  Rajat Raina,et al.  Efficient sparse coding algorithms , 2006, NIPS.

[15]  Malur K. Sundareshan,et al.  Superresolution of passive millimeter-wave images using a combined maximum-likelihood optimization and projection-onto-convex-sets approach , 2001, SPIE Defense + Commercial Sensing.

[16]  Chao Wang,et al.  Feature extraction using constrained maximum variance mapping , 2008, Pattern Recognit..

[17]  D.-S. Huang,et al.  Radial Basis Probabilistic Neural Networks: Model and Application , 1999, Int. J. Pattern Recognit. Artif. Intell..

[18]  De-Shuang Huang,et al.  A Constructive Hybrid Structure Optimization Methodology for Radial Basis Probabilistic Neural Networks , 2008, IEEE Transactions on Neural Networks.

[19]  De-Shuang Huang,et al.  An improved approximation approach incorporating particle swarm optimization and a priori information into neural networks , 2010, Neural Computing and Applications.

[20]  Li Shang,et al.  L-R restoration method of millimeter wave image based on NNSC shrinkage technique , 2011, 2011 4th International Congress on Image and Signal Processing.

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

[22]  Simon C. K. Shiu,et al.  Metasample-Based Sparse Representation for Tumor Classification , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[23]  Yunhui Shi,et al.  Single-Image Super-Resolution Based on Decomposition and Sparse Representation , 2010, 2010 International Conference on Multimedia Communications.

[24]  Zheng Xin.  Maximum Likelihood Frequency Domain Correction Super-resolution Algorithm for Passive Millimeter Wave Imaging , 2009 .

[25]  Pingang Su,et al.  Active MMW Focal Plane Imaging System , 2009, ICIC.

[26]  Zhixun Su,et al.  Learning PDEs for Image Restoration via Optimal Control , 2010, ECCV.

[27]  Simon C. K. Shiu,et al.  Molecular Pattern Discovery Based on Penalized Matrix Decomposition , 2011, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[28]  Yu Jing,et al.  A Novel Fast Algorithm for MAP Super-Resolution Image Reconstruction , 2009 .

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

[30]  De-Shuang Huang,et al.  Locally linear discriminant embedding: An efficient method for face recognition , 2008, Pattern Recognit..

[31]  Xiaofeng Wang,et al.  A Novel Density-Based Clustering Framework by Using Level Set Method , 2009, IEEE Transactions on Knowledge and Data Engineering.