Augmented Coupled Dictionary Learning for Image Super-Resolution

Size: px
Start display at page:

Download "Augmented Coupled Dictionary Learning for Image Super-Resolution"

Transcription

1 Augmented Coupled Dictionary Learning for Image Super-Resolution Muhammad Rushdi and Jeffrey Ho Computer and Information Science and Engineering University of Florida Gainesville, Florida, U.S.A. Abstract Recent approaches in image super-resolution suggest learning dictionary pairs to model the relationship between low-resolution and high-resolution image patches with sparsity constraints on the patch representation. Most of the previous approaches in this direction assume for simplicity that the sparse codes for a low-resolution patch are equal to those of the corresponding high-resolution patch. However, this invariance assumption is not quite accurate especially for large scaling factors where the optimal weights and indices of representative features are not fixed across the scaling transformation. In this paper, we propose an augmented coupled dictionary learning scheme that compensates for the inaccuracy of the invariance assumption. First, we learn a dictionary for the low-resolution image space. Then, we compute an augmented dictionary in the high-resolution image space where novel augmented dictionary atoms are inferred from the training error of the low-resolution dictionary. For a low-resolution test image, the sparse codes of the low-resolution patches and the lowresolution dictionary training error are combined with the trained high-resolution dictionary to produce a high-resolution image. Our experimental results compare favourably with the non-augmented scheme. Keywords-dictionary learning; coupled features; superresolution; I. INTRODUCTION The availability of high-resolution (HR) degradation-free images is highly important for the success of many applications in medicine ( [10], [11]), remote sensing [6], biometric identification [15], and other fields. However, high-resolution imaging devices are still quite expensive. As well, the storage and transmission of high-resolution images are limited by space and bandwidth considerations. On the other hand, while low-resolution (LR) images are cheap to capture, store, and transmit, they still suffer from loss of details, blurring, noise, and interference. Superresolution (SR) techniques aim at creating high-resolution images from low-resolution ones while overcoming the inherent limitations of low-resolution imaging [8]. However, this is an ill-posed problem since one low-resolution patch can correspond to many high-resolution patches. Moreover, the low-resolution observations are blurred, noisy, and misaligned. So, interpolation, reconstruction and example-based techniques have been proposed to regularize the solution [2]. Example-based techniques learn the mapping between the low- and high-resolution patches from a training dataset and apply this mapping to low-resolution patches of test images [3], [4]. Dictionary learning schemes improve these techniques by relating the low- and high-resolution features through sparse representations with respect to coupled overcomplete dictionaries [13], [14], [16], [12], [7]. A simplifying assumption of these schemes is the invariance of the sparse representation: the sparse codes of a lowresolution patch with respect to the low-resolution dictionary are identical to the sparse codes of the corresponding highresolution patch with respect to the high-resolution dictionary. Nevertheless, this assumption is inaccurate and does not hold in particular for large magnification factors. Jia et al [5] relax this assumption by allowing the sparse codes of low- and high-resolution patch pairs to have different values while they still share the same support. Wang et al [9] learn a linear map between the sparse codes of the low- and high-resolution patches. In this paper, we compensate for the inaccuracy of the invariance assumption of sparse representations by explicitly incorporating the lowresolution dictionary learning error in the high-resolution image reconstruction model. In particular, we augment the high-resolution dictionary with additional atoms that relate the residual error of the low-resolution dictionary to the high-resolution patches. Our experiments show that this augmented dictionary models better the LR-HR coupling and outperforms the basic coupled dictionary learning. As well, we show how the dimensionality of the low-resolution features affects the augmented dictionary scheme. In Section II, we review the coupled dictionary learning () approach then introduce our augmented coupled dictionary learning () and synthesis approach. We compare the superresolution performance of our method with the baseline approach in Section III. Conclusions and future work are given in Section IV. II. DICTIONARY AUGMENTATION FOR COUPLED SPACES A. Problem Formulation Suppose we are given two coupled feature spaces, the high-resolution patch spacex R nx and the low-resolution feature space Y R ny, tied by a certain mapping function F that may be non-linear and unknown. The goal of dictionary learning approaches is to learn two dictionaries D x R nx K and D y R ny K for X and Y such that

2 the sparse representation of x i X in terms of D x should be related by a map W (chosen typically as the identity map for simplicity) to that of y i Y in terms of D y, where y i = F(x i ). Yang et al [14] addressed this problem by generalizing the basic sparse coding scheme to minimize D x,d y,γ subject to X D x Γ 2 F + Y D y Γ 2 F +λ Γ 1 { k Dx (:,k) 2 1 D y (:,k) 2 1. where X R nx N and Y R ny N are data matrices from the high-resolution patch space X and the lowresolution feature space Y, respectively. Γ R K N are the data sparse codes (common to both dictionaries) and λ is a regularization parameter. The identity-map assumption between the spare representations of the features in the low- and high-resolution spaces is rather restrictive and inaccurate for large super-resolution factors. We can alleviate this problem and get a more truthful dictionary model by augmenting the high-resolution space dictionary D x with an augmenting dictionary D a R nx ny. The augmenting dictionary should compensate for the modelling error of the non-augmented coupled dictionary scheme. This modelling error can be defined as the lowresolution-space dictionary learning residual (1) R = Y D y Γ. (2) The augmenting dictionary D a atoms may be selected to minimize this residual R. So, the Augmented Coupled Dictionary Learning () objective function may be formulated as minimize X D xγ D a R 2 F + Y D y Γ 2 F +λ Γ 1 D x,d a,d y,γ D y, compute the low-resolution residual R t = Y t D y Γ t, then compute the high-resolution image patches as subject to B. Dictionary Training k D x (:,k) 2 1 D y (:,k) 2 1 j D a (:,j) 2 1. The energy minimization in Equation 3 is tackled by separating the objective function into three sub-problems, namely updating the sparse codes Γ of the low-resolutionspace training samples Y, updating the low-resolution-space dictionary D y, and hence jointly constructing the highresolution-space and the augmenting dictionaries D x, D a. C. Optimization for the Low-Resolution Dictionary The first two sub-problems are solved through the K- SVD dictionary training procedure [1]. In this procedure, the sparse coding and dictionary update are alternated to solve the decoupled problem (3) minimize D y,γ subject to Y D y Γ 2 F +λ Γ 1 { k Dy (:,k) 2 1. The outputs of the K-SVD procedure are the lowresolution-space dictionary D y and the sparse codes Γ of the the low-resolution training data Y with respect to this dictionary. D. Computing the High-Resolution and Augmenting Dictionaries Once the low-resolution dictionary D y and the sparse codesγof the training data are obtained, the high-resolution and augmenting dictionaries could be easily obtained from Let and (4) minimize D x,d a X D x Γ D a R 2 F (5) Φ = ( D x D a ) (6) Λ = ( Γ). (7) R Then the solution of Equation 5 is the pseudo-inverse expression E. Synthesis Φ = XΛ = XΛ T (ΛΛ T ) 1. (8) Given a test image, we extract the low-resolution features Y t from the image patches, find the sparse codes Γ t of the features with respect to trained low-resolution dictionary X t = D x Γ t +D a R t. (9) The high-resolution image patches are then put back in their respective locations and averaged in overlapping areas to produce the output image. A. Implementation Details III. EXPERIMENTAL RESULTS For dictionary training, we used the natural image dataset provided by [13]. The dataset consists of 91 images of flowers, faces, vehicles, and other natural scenes. Since the human visual system is more sensitive to the luminance information, we convert all training images to gray-level ones and discard the color information. Regrading the images as the high-resolution examples, we blur and downsample all images with a factor of 3. The downsampled images are then upscaled back to their original sizes to simplify the

3 algorithmic details. The upscaled images have lost highresolution details during the downsampling process and this why these images are considered to be of low resolution. Following [13], [14], four horizontal and vertical derivative filters (namely,f 1 = [ 1,0,1] = f T 2,f 3 = [1,0, 2,0,1] = f T 4 ) are applied to the LR images to extract localized highfrequency content. Patches of size 9 9 are extracted from the filtered images. The patches are stacked together forming 324-dimensional feature vectors. Then PCA is applied to ignore components that contribute no more than 0.1% of the average feature energy. This reduces the LR dimensionality to 30. For the high-resolution images, low frequencies are removed by subtracting each low-resolution (upscaled) image from its high-resolution counterpart. About 130,000 LR-HR pairs are extracted (20% of which are used for validation). We compare our method against bicubic interpolation as well as the basic coupled dictionary learning () variant of Zeyde et al [16]. For both dictionary learning schemes, we use a total high-resolution dictionary size of 2048 atoms, 40 iterations of the K-SVD algorithm, and a maximal sparsity of 3 for the OMP coding scheme. B. Quantitative and Visual Comparison We tested the super-resolution performance on 14 standard test images and computed the average quality metrics. For each image, the dictionary-based synthesis was applied to the luminance channel while bicubic interpolation was applied to the chrominance channels. Table I shows the Structural Similarity Index (SSIM) and the Peak Signal-to- Noise Ratio (PSNR) measures in the first and second row for each image respectively. Our augmented dictionary learning scheme surpasses the baseline coupled dictionary learning on all 14 images. On average, our scheme and the baseline one show an improvement over bicubic interpolation of db and db, respectively. Figure 4 shows samples of the ground-truth and reconstructed test images. Our results look sharper than those of the bicubic interpolation and are also visually better or similar to their counterparts in the baseline scheme. Figure 3 shows the trained dictionaries of the augmented scheme. The augmenting dictionary shows clear structures and improves the overall super-resolution quality although it is small in size. C. Effect of the High-Resolution Dictionary Size We explore the effect of the HR dictionary size in Figure 1. Dictionary sizes of 128, 256, 512, 1024, and 2048 are used. The average SSIM and PSNR measures (Figure 1a,b) of our augmented scheme are consistently better across all dictionary size values. This comes at no cost in synthesis time. Indeed, our average synthesis time is slightly less than that of the baseline scheme (Figure 1c) since for the same total number of HR dictionary atoms, our scheme allocates fewer atoms to the over-complete dictionary and hence reduces the sparse coding complexity (which is known to be the bottleneck of the K-SVD algorithm). D. Effect of the Low-Resolution Feature Dimensionality From Equation 3, we see that the number of augmenting dictionary D a atoms depends on the dimensionality of the LR feature vectors which in turn can be controlled through the PCA dimensionality reduction step. Figure 2 shows the dependence of the average performance metrics on the amount of discarded feature energy. On one hand, for a large percentage of discarded energy, there is a clear drop in the average performance metrics. Indeed, the performance gap between the augmented and baseline schemes gets smaller since the augmenting dictionary will have very few atoms in this case. On the other hand, for small percentages of the discarded energy, there is no noticeable improvement over the mid-range values but there is a big increase in average synthesis time. So, a discarded energy percentage of 0.1% is a reasonable trade-off here between accuracy and time complexity. IV. CONCLUSIONS AND FUTURE WORK In this work, we have introduced a novel coupled dictionary learning scheme for image super-resolution. Our scheme models more accurately the relation between lowresolution and high-resolution patches by incorporating an augmenting dictionary that links the low-resolution reconstruction error to the high-resolution dictionary model. We have shown that the new model produces improved superresolution results in comparison with the standard coupled dictionary learning scheme. For future work, we plan to put reasonable structural constraints on the augmenting dictionary to better capture relevant features in the residual data and to bound the time and space complexity in the case of large dictionary sizes. Moreover, we would like to explore more generalized coupled dictionary models for image super-resolution and similar applications. REFERENCES [1] M. Aharon, M. Elad, and A. Bruckstein. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. Signal Processing, IEEE Transactions on, 54(11): , nov. 6. [2] G. Cristóbal, E. Gil, F. Šroubek, J. Flusser, C. Miravet, and F. B. Rodríguez. Superresolution imaging: a survey of current techniques. In Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, volume 7074 of Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, Aug. 8. [3] W. Freeman, T. Jones, and E. Pasztor. Example-based superresolution. Computer Graphics and Applications, IEEE, 22(2):56 65, mar/apr 2. [4] D. Glasner, S. Bagon, and M. Irani. Super-resolution from a single image. In ICCV, 9. [5] K. Jia, X. Tang, and X. Wang. Image transformation based on learning dictionaries across image spaces. Pattern Analysis and Machine Intelligence, IEEE Transactions on, PP(99):1, 2012.

4 (a) Original: foreman (b) : ( ) (e) Original: monarch (f) : ( ) (d) : ( ) (g) :0.9802(29.535) 3 (j) : (22.439) (k) : ( ) 5 (n) : ( ) (o) : ( ) Figure 4. 3 (v) : (25.912) (s) : ( ) (r) : (24.365) (u) Original: flowers (p) : ( ) (l) : ( ) (q) Original: barbara (h) :0.9809( ) (m) Original: zebra (i) Original: ppt3 (c) : (31.918) 3 (w) : ( ) (t) :0.8963( ) 4 3 (x) : (27.306) Visual results for sample test images. Quantitative metrics are shown as SSIM(PSNR). 4

5 Average PSNR Average PSNR HR Dictionary Size Discarded LR feature energy (a) Average PSNR (a) Average PSNR Average SSIM Average SSIM HR Dictionary Size Discarded LR feature energy (b) Average SSIM (b) Average SSIM Average Time 6 Average Time HR Dictionary Size Discarded LR feature energy (c) Average Synthesis Time (c) Average Synthesis Time Figure 1. Effect of the HR dictionary size on the average super-resolution performance metrics of 14 test images. Figure 2. Effect of the dimensionality of the LR features on the average SR performance metrics of 14 test images.

6 (a) Low-Resolution Dictionary (b) High-Resolution Dictionary bicubic [16] baboon barbara bridge coastguard comic face flowers foreman lenna man monarch pepper ppt zebra Average Table I SUPER-RESOLUTION QUANTITATIVE RESULTS. THE SSIM AND PSNR MEASURES ARE SHOWN FOR EACH IMAGE IN THE 1ST AND 2ND ROWS, RESPECTIVELY. (c) Augmenting High-Resolution Dictionary Figure 3. The trained dictionaries of the augmented coupled dictionary learning () scheme. [6] F. Li, X. Jia, D. Fraser, and A. Lambert. Super resolution for remote sensing images based on a universal hidden markov tree model. Geoscience and Remote Sensing, IEEE Transactions on, 48(3): , march [7] D. Lin and X. Tang. Coupled space learning of image style transformation. In Computer Vision, 5. ICCV 5. Tenth IEEE International Conference on, volume 2, pages Vol. 2, oct. 5. [8] S. C. Park, M. K. Park, and M. G. Kang. Super-resolution image reconstruction: a technical overview. Signal Processing Magazine, IEEE, 20(3):21 36, may 3. [9] Y. L. S. Wang, L. Zhang and Q. Pan. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch image synthesis. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), [10] B. Scherrer, A. Gholipour, and S. K. Warfield. Superresolution reconstruction of diffusion-weighted images from distortion compensated orthogonal anisotropic acquisitions. In Mathematical Methods in Biomedical Image Analysis (MMBIA), 2012 IEEE Workshop on, pages , jan [11] D. Wallach, F. Lamare, G. Kontaxakis, and D. Visvikis. Super-resolution in respiratory synchronized positron emission tomography. Medical Imaging, IEEE Transactions on, 31(2): , feb [12] J. Yang, Z. Wang, Z. Lin, S. Cohen, and T. Huang. Couple dictionary training for image super-resolution. Image Processing, IEEE Transactions on, PP(99):1, [13] J. Yang, J. Wright, T. Huang, and Y. Ma. Image superresolution as sparse representation of raw image patches. In Computer Vision and Pattern Recognition, 8. CVPR 8. IEEE Conference on, pages 1 8, june 8. [14] J. Yang, J. Wright, T. Huang, and Y. Ma. Image superresolution via sparse representation. Image Processing, IEEE Transactions on, 19(11): , nov [15] X. Zeng and H. Huang. Super-resolution method for multiview face recognition from a single image per person using nonlinear mappings on coherent features. Signal Processing Letters, IEEE, 19(4): , april [16] R. Zeyde, M. Elad, and M. Protter. On single image scale-up using sparse-representations. In Curves and Surfaces, pages , 2010.

Single-Image Super-Resolution Using Multihypothesis Prediction

Single-Image Super-Resolution Using Multihypothesis Prediction Single-Image Super-Resolution Using Multihypothesis Prediction Chen Chen and James E. Fowler Department of Electrical and Computer Engineering, Geosystems Research Institute (GRI) Mississippi State University,

More information

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution Anchored Neighborhood Regression for Fast Example-Based Super-Resolution Radu Timofte 1,2, Vincent De Smet 1, and Luc Van Gool 1,2 1 KU Leuven, ESAT-PSI / iminds, VISICS 2 ETH Zurich, D-ITET, Computer

More information

IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCE

IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCE IMAGE SUPER-RESOLUTION BASED ON DICTIONARY LEARNING AND ANCHORED NEIGHBORHOOD REGRESSION WITH MUTUAL INCOHERENCE Yulun Zhang 1, Kaiyu Gu 2, Yongbing Zhang 1, Jian Zhang 3, and Qionghai Dai 1,4 1 Shenzhen

More information

On Single Image Scale-Up using Sparse-Representation

On Single Image Scale-Up using Sparse-Representation On Single Image Scale-Up using Sparse-Representation Roman Zeyde, Matan Protter and Michael Elad The Computer Science Department Technion Israel Institute of Technology Haifa 32000, Israel {romanz,matanpr,elad}@cs.technion.ac.il

More information

Learning based face hallucination techniques: A survey

Learning based face hallucination techniques: A survey Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)

More information

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang

A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network. Zhe Li, Shu Li, Jianmin Wang and Hongyang Wang 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016) A Novel Multi-Frame Color Images Super-Resolution Framewor based on Deep Convolutional Neural Networ Zhe Li, Shu

More information

Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution

Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution Enhancing DubaiSat-1 Satellite Imagery Using a Single Image Super-Resolution Saeed AL-Mansoori 1 and Alavi Kunhu 2 1 Associate Image Processing Engineer, SIPAD Image Enhancement Section Emirates Institution

More information

Single Image Super-Resolution via Sparse Representation over Directionally Structured Dictionaries Based on the Patch Gradient Phase Angle

Single Image Super-Resolution via Sparse Representation over Directionally Structured Dictionaries Based on the Patch Gradient Phase Angle 2014 UKSim-AMSS 8th European Modelling Symposium Single Image Super-Resolution via Sparse Representation over Directionally Structured Dictionaries Based on the Patch Gradient Phase Angle Mahmoud Nazzal,

More information

A Single Image Compression Framework Combined with Sparse Representation-Based Super- Resolution

A Single Image Compression Framework Combined with Sparse Representation-Based Super- Resolution International Conference on Electronic Science and Automation Control (ESAC 2015) A Single Compression Framework Combined with Sparse RepresentationBased Super Resolution He Xiaohai, He Jingbo, Huang Jianqiu

More information

Image Interpolation using Collaborative Filtering

Image Interpolation using Collaborative Filtering Image Interpolation using Collaborative Filtering 1,2 Qiang Guo, 1,2,3 Caiming Zhang *1 School of Computer Science and Technology, Shandong Economic University, Jinan, 250014, China, qguo2010@gmail.com

More information

arxiv: v1 [cs.cv] 3 Jan 2017

arxiv: v1 [cs.cv] 3 Jan 2017 Learning a Mixture of Deep Networks for Single Image Super-Resolution Ding Liu, Zhaowen Wang, Nasser Nasrabadi, and Thomas Huang arxiv:1701.00823v1 [cs.cv] 3 Jan 2017 Beckman Institute, University of Illinois

More information

Fast single image super-resolution based on sigmoid transformation

Fast single image super-resolution based on sigmoid transformation > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 1 Fast single image super-resolution based on sigmoid transformation Longguang Wang, Zaiping Lin, Jinyan Gao, Xinpu

More information

Boosting face recognition via neural Super-Resolution

Boosting face recognition via neural Super-Resolution Boosting face recognition via neural Super-Resolution Guillaume Berger, Cle ment Peyrard and Moez Baccouche Orange Labs - 4 rue du Clos Courtel, 35510 Cesson-Se vigne - France Abstract. We propose a two-step

More information

SUPER-RESOLUTION RECONSTRUCTION OF CARDIAC MRI BY USING COUPLED DICTIONARY LEARNING

SUPER-RESOLUTION RECONSTRUCTION OF CARDIAC MRI BY USING COUPLED DICTIONARY LEARNING SUPER-RESOLUTION RECONSTRUCTION OF CARDIAC MRI BY USING COUPLED DICTIONARY LEARNING Gaddala Pratibha (M.Tech.) 1 A. Syam Kumar (Asst.Professor And M.Tech) 2 Nalanda Institute of Engineering and Technology,

More information

Hybrid Video Compression Using Selective Keyframe Identification and Patch-Based Super-Resolution

Hybrid Video Compression Using Selective Keyframe Identification and Patch-Based Super-Resolution 2011 IEEE International Symposium on Multimedia Hybrid Video Compression Using Selective Keyframe Identification and Patch-Based Super-Resolution Jeffrey Glaister, Calvin Chan, Michael Frankovich, Adrian

More information

Single Image Super-Resolution via Iterative Collaborative Representation

Single Image Super-Resolution via Iterative Collaborative Representation Single Image Super-Resolution via Iterative Collaborative Representation Yulun Zhang 1(B), Yongbing Zhang 1, Jian Zhang 2, aoqian Wang 1, and Qionghai Dai 1,3 1 Graduate School at Shenzhen, Tsinghua University,

More information

Single image super-resolution by directionally structured coupled dictionary learning

Single image super-resolution by directionally structured coupled dictionary learning Ahmed and Shah EURASIP Journal on Image and Video Processing (2016) 2016:36 DOI 10.1186/s13640-016-0141-6 EURASIP Journal on Image and Video Processing RESEARCH Open Access Single image super-resolution

More information

Exploiting Self-Similarities for Single Frame Super-Resolution

Exploiting Self-Similarities for Single Frame Super-Resolution Exploiting Self-Similarities for Single Frame Super-Resolution Chih-Yuan Yang Jia-Bin Huang Ming-Hsuan Yang Electrical Engineering and Computer Science University of California at Merced Merced, CA 95343,

More information

arxiv: v1 [cs.cv] 6 Nov 2015

arxiv: v1 [cs.cv] 6 Nov 2015 Seven ways to improve example-based single image super resolution Radu Timofte Computer Vision Lab D-ITET, ETH Zurich timofter@vision.ee.ethz.ch Rasmus Rothe Computer Vision Lab D-ITET, ETH Zurich rrothe@vision.ee.ethz.ch

More information

SUPER RESOLUTION RECONSTRUCTION OF CARDIAC MRI USING COUPLED DICTIONARY LEARNING

SUPER RESOLUTION RECONSTRUCTION OF CARDIAC MRI USING COUPLED DICTIONARY LEARNING SUPER RESOLUTION RECONSTRUCTION OF CARDIAC MRI USING COUPLED DICTIONARY LEARNING Abstract M. Vinod Kumar (M.tech) 1 V. Gurumurthy Associate Professor, M.Tech (Ph.D) 2 Dr.M. Narayana, Professor, Head of

More information

FAST SINGLE-IMAGE SUPER-RESOLUTION WITH FILTER SELECTION. Image Processing Lab Technicolor R&I Hannover

FAST SINGLE-IMAGE SUPER-RESOLUTION WITH FILTER SELECTION. Image Processing Lab Technicolor R&I Hannover FAST SINGLE-IMAGE SUPER-RESOLUTION WITH FILTER SELECTION Jordi Salvador Eduardo Pérez-Pellitero Axel Kochale Image Processing Lab Technicolor R&I Hannover ABSTRACT This paper presents a new method for

More information

Efficient Module Based Single Image Super Resolution for Multiple Problems

Efficient Module Based Single Image Super Resolution for Multiple Problems Efficient Module Based Single Image Super Resolution for Multiple Problems Dongwon Park Kwanyoung Kim Se Young Chun School of ECE, Ulsan National Institute of Science and Technology, 44919, Ulsan, South

More information

Deep Back-Projection Networks For Super-Resolution Supplementary Material

Deep Back-Projection Networks For Super-Resolution Supplementary Material Deep Back-Projection Networks For Super-Resolution Supplementary Material Muhammad Haris 1, Greg Shakhnarovich 2, and Norimichi Ukita 1, 1 Toyota Technological Institute, Japan 2 Toyota Technological Institute

More information

Ms.DHARANI SAMPATH Computer Science And Engineering, Sri Krishna College Of Engineering & Technology Coimbatore, India

Ms.DHARANI SAMPATH Computer Science And Engineering, Sri Krishna College Of Engineering & Technology Coimbatore, India Improving Super Resolution of Image by Multiple Kernel Learning Ms.DHARANI SAMPATH Computer Science And Engineering, Sri Krishna College Of Engineering & Technology Coimbatore, India dharanis012@gmail.com

More information

Image Deblurring Using Adaptive Sparse Domain Selection and Adaptive Regularization

Image Deblurring Using Adaptive Sparse Domain Selection and Adaptive Regularization Volume 3, No. 3, May-June 2012 International Journal of Advanced Research in Computer Science RESEARCH PAPER Available Online at www.ijarcs.info ISSN No. 0976-5697 Image Deblurring Using Adaptive Sparse

More information

Optimized Super Resolution Reconstruction Framework for Cardiac MRI Images Perception

Optimized Super Resolution Reconstruction Framework for Cardiac MRI Images Perception Optimized Super Resolution Reconstruction Framework for Cardiac MRI Images Perception 1 P.Hari Prasad, 2 N. Suresh, 3 S. Koteswara Rao 1 Asist, Decs, JNTU Kakinada, Vijayawada, Krishna (Dist), Andhra Pradesh

More information

Image Super-Resolution Reconstruction Based On L 1/2 Sparsity

Image Super-Resolution Reconstruction Based On L 1/2 Sparsity Buletin Teknik Elektro dan Informatika (Bulletin of Electrical Engineering and Informatics) Vol. 3, No. 3, September 4, pp. 55~6 ISSN: 89-39 55 Image Super-Resolution Reconstruction Based On L / Sparsity

More information

Image Restoration and Background Separation Using Sparse Representation Framework

Image Restoration and Background Separation Using Sparse Representation Framework Image Restoration and Background Separation Using Sparse Representation Framework Liu, Shikun Abstract In this paper, we introduce patch-based PCA denoising and k-svd dictionary learning method for the

More information

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution Yan Huang 1 Wei Wang 1 Liang Wang 1,2 1 Center for Research on Intelligent Perception and Computing National Laboratory of

More information

Learning a Deep Convolutional Network for Image Super-Resolution

Learning a Deep Convolutional Network for Image Super-Resolution Learning a Deep Convolutional Network for Image Super-Resolution Chao Dong 1, Chen Change Loy 1, Kaiming He 2, and Xiaoou Tang 1 1 Department of Information Engineering, The Chinese University of Hong

More information

Robust Single Image Super-resolution based on Gradient Enhancement

Robust Single Image Super-resolution based on Gradient Enhancement Robust Single Image Super-resolution based on Gradient Enhancement Licheng Yu, Hongteng Xu, Yi Xu and Xiaokang Yang Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai 200240,

More information

Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform

Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform Self-Learning of Edge-Preserving Single Image Super-Resolution via Contourlet Transform Min-Chun Yang, De-An Huang, Chih-Yun Tsai, and Yu-Chiang Frank Wang Dept. Computer Science and Information Engineering,

More information

MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo

MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS Yanghao Li, Jiaying Liu, Wenhan Yang, Zongg Guo Institute of Computer Science and Technology, Peking University, Beijing, P.R.China,

More information

A Self-Learning Optimization Approach to Single Image Super-Resolution using Kernel ridge regression model

A Self-Learning Optimization Approach to Single Image Super-Resolution using Kernel ridge regression model A Self-Learning Optimization Approach to Single Image Super-Resolution using Kernel ridge regression model Ms. Dharani S 1 PG Student (CSE), Sri Krishna College of Engineering and Technology, Anna University,

More information

SUPER-RESOLUTION RECONSTRUCTION ALGORITHM FOR BASED ON COUPLED DICTIONARY LEARNING CARDIAC MRI RECONSTRUCTION

SUPER-RESOLUTION RECONSTRUCTION ALGORITHM FOR BASED ON COUPLED DICTIONARY LEARNING CARDIAC MRI RECONSTRUCTION SUPER-RESOLUTION RECONSTRUCTION ALGORITHM FOR BASED ON COUPLED DICTIONARY LEARNING CARDIAC MRI RECONSTRUCTION M.PRATHAP KUMAR, Email Id: Prathap.Macherla@Gmail.Com J.VENKATA LAKSHMI, M.Tech, Asst.Prof,

More information

Patch-Based Color Image Denoising using efficient Pixel-Wise Weighting Techniques

Patch-Based Color Image Denoising using efficient Pixel-Wise Weighting Techniques Patch-Based Color Image Denoising using efficient Pixel-Wise Weighting Techniques Syed Gilani Pasha Assistant Professor, Dept. of ECE, School of Engineering, Central University of Karnataka, Gulbarga,

More information

Comparative Analysis of Edge Based Single Image Superresolution

Comparative Analysis of Edge Based Single Image Superresolution Comparative Analysis of Edge Based Single Image Superresolution Sonali Shejwal 1, Prof. A. M. Deshpande 2 1,2 Department of E&Tc, TSSM s BSCOER, Narhe, University of Pune, India. ABSTRACT: Super-resolution

More information

Introduction to Image Super-resolution. Presenter: Kevin Su

Introduction to Image Super-resolution. Presenter: Kevin Su Introduction to Image Super-resolution Presenter: Kevin Su References 1. S.C. Park, M.K. Park, and M.G. KANG, Super-Resolution Image Reconstruction: A Technical Overview, IEEE Signal Processing Magazine,

More information

Super-Resolution Rebuilding Of Cardiac MRI Using Coupled Dictionary Analyzing

Super-Resolution Rebuilding Of Cardiac MRI Using Coupled Dictionary Analyzing Super-Resolution Rebuilding Of Cardiac MRI Using Coupled Dictionary Analyzing VALLAKATI MADHAVI 1 CE&SP (ECE) Osmania University, HYDERABAD chittymadhavi92@gmail.com MRS.SHOBA REDDY 2 P.HD OsmaniaUniversity,

More information

arxiv: v1 [cs.cv] 8 Feb 2018

arxiv: v1 [cs.cv] 8 Feb 2018 DEEP IMAGE SUPER RESOLUTION VIA NATURAL IMAGE PRIORS Hojjat S. Mousavi, Tiantong Guo, Vishal Monga Dept. of Electrical Engineering, The Pennsylvania State University arxiv:802.0272v [cs.cv] 8 Feb 208 ABSTRACT

More information

Image Super-Resolution Using Compressed Sensing Based on Learning Sub Dictionary

Image Super-Resolution Using Compressed Sensing Based on Learning Sub Dictionary Image Super-Resolution Using Compressed Sensing Based on Learning Sub Dictionary 1 MUHAMMAD SAMEER SHEIKH, 1 QUNSHENG CAO, 2 CAIYUN WANG 1 College of Electronics and Information Engineering, 2 College

More information

A HYBRID WAVELET CONVOLUTION NETWORK WITH SPARSE-CODING FOR IMAGE SUPER-RESOLUTION

A HYBRID WAVELET CONVOLUTION NETWORK WITH SPARSE-CODING FOR IMAGE SUPER-RESOLUTION A HYBRI WAVELET CONVOLUTION NETWORK WITH SPARSE-COING FOR IMAGE SUPER-RESOLUTION Xing Gao Hongkai Xiong epartment of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China ABSTRACT

More information

This is a repository copy of Face image super-resolution via weighted patches regression.

This is a repository copy of Face image super-resolution via weighted patches regression. This is a repository copy of Face image super-resolution via weighted patches regression. White Rose Research Online URL for this paper: http://eprints.whiterose.ac.uk/115963/ Version: Accepted Version

More information

PATCH BASED COUPLED DICTIONARY APPROACH FOR CARDIAC MRI IMAGES USING SR RECONSTRUCTION ALGORITHM

PATCH BASED COUPLED DICTIONARY APPROACH FOR CARDIAC MRI IMAGES USING SR RECONSTRUCTION ALGORITHM PATCH BASED COUPLED DICTIONARY APPROACH FOR CARDIAC MRI IMAGES USING SR RECONSTRUCTION ALGORITHM G.Priyanka 1, B.Narsimhareddy 2, K.Bhavitha 3, M.Deepika 4,A.Sai Reddy 5 and S.RamaKoteswaraRao 6 1,2,3,4,5

More information

Single-image super-resolution in RGB space via group sparse representation

Single-image super-resolution in RGB space via group sparse representation Published in IET Image Processing Received on 10th April 2014 Revised on 22nd September 2014 Accepted on 15th October 2014 ISSN 1751-9659 Single-image super-resolution in RGB space via group sparse representation

More information

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Qi Zhang & Yan Huang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition

More information

Robust Video Super-Resolution with Registration Efficiency Adaptation

Robust Video Super-Resolution with Registration Efficiency Adaptation Robust Video Super-Resolution with Registration Efficiency Adaptation Xinfeng Zhang a, Ruiqin Xiong b, Siwei Ma b, Li Zhang b, Wen Gao b a Institute of Computing Technology, Chinese Academy of Sciences,

More information

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N.

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. Dartmouth, MA USA Abstract: The significant progress in ultrasonic NDE systems has now

More information

A Sparse Coding based Approach for the Resolution Enhancement and Restoration of Printed and Handwritten Textual Images

A Sparse Coding based Approach for the Resolution Enhancement and Restoration of Printed and Handwritten Textual Images A Sparse Coding based Approach for the Resolution Enhancement and Restoration of Printed and Handwritten Textual Images Rim Walha, Fadoua Drira and Adel M. Alimi University of Sfax, ENI-Sfax, REGIM Sfax,

More information

A Statistical Prediction Model Based on Sparse

A Statistical Prediction Model Based on Sparse A Statistical Prediction Model Based on Sparse 1 Representations for Single Image Super-Resolution Tomer Peleg Student Member, IEEE and Michael Elad Fellow, IEEE Abstract We address single image super-resolution

More information

Super-resolution using Neighbor Embedding of Back-projection residuals

Super-resolution using Neighbor Embedding of Back-projection residuals Super-resolution using Neighbor Embedding of Back-projection residuals Marco Bevilacqua, Aline Roumy, Christine Guillemot SIROCCO Research team INRIA Rennes, France {marco.bevilacqua, aline.roumy, christine.guillemot}@inria.fr

More information

Example-Based Image Super-Resolution Techniques

Example-Based Image Super-Resolution Techniques Example-Based Image Super-Resolution Techniques Mark Sabini msabini & Gili Rusak gili December 17, 2016 1 Introduction With the current surge in popularity of imagebased applications, improving content

More information

Speed up a Machine-Learning-based Image Super-Resolution Algorithm on GPGPU

Speed up a Machine-Learning-based Image Super-Resolution Algorithm on GPGPU Speed up a Machine-Learning-based Image Super-Resolution Algorithm on GPGPU Ke Ma 1, and Yao Song 2 1 Department of Computer Sciences 2 Department of Electrical and Computer Engineering University of Wisconsin-Madison

More information

Improved Feature Selection for Neighbor Embedding Super-Resolution Using Zernike Moments

Improved Feature Selection for Neighbor Embedding Super-Resolution Using Zernike Moments Improved Feature Selection for Neighbor Embedding Super-Resolution Using Zernike Moments Deepasikha Mishra, Banshidhar Majhi and Pankaj Kumar Sa Abstract This paper presents a new feature selection method

More information

A A A. Fig.1 image patch. Then the edge gradient magnitude is . (1)

A A A. Fig.1 image patch. Then the edge gradient magnitude is . (1) International Conference on Information Science and Computer Applications (ISCA 013) Two-Dimensional Barcode Image Super-Resolution Reconstruction Via Sparse Representation Gaosheng Yang 1,Ningzhong Liu

More information

Extended Dictionary Learning : Convolutional and Multiple Feature Spaces

Extended Dictionary Learning : Convolutional and Multiple Feature Spaces Extended Dictionary Learning : Convolutional and Multiple Feature Spaces Konstantina Fotiadou, Greg Tsagkatakis & Panagiotis Tsakalides kfot@ics.forth.gr, greg@ics.forth.gr, tsakalid@ics.forth.gr ICS-

More information

Super-Resolution Image with Estimated High Frequency Compensated Algorithm

Super-Resolution Image with Estimated High Frequency Compensated Algorithm Super-Resolution with Estimated High Frequency Compensated Algorithm Jong-Tzy Wang, 2 Kai-Wen Liang, 2 Shu-Fan Chang, and 2 Pao-Chi Chang 1 Department of Electronic Engineering, Jinwen University of Science

More information

NTHU Rain Removal Project

NTHU Rain Removal Project People NTHU Rain Removal Project Networked Video Lab, National Tsing Hua University, Hsinchu, Taiwan Li-Wei Kang, Institute of Information Science, Academia Sinica, Taipei, Taiwan Chia-Wen Lin *, Department

More information

Bilevel Sparse Coding

Bilevel Sparse Coding Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional

More information

Seven ways to improve example-based single image super resolution

Seven ways to improve example-based single image super resolution Seven ways to improve example-based single image super resolution Radu Timofte CVL, D-ITET, ETH Zurich radu.timofte@vision.ee.ethz.ch Rasmus Rothe CVL, D-ITET, ETH Zurich rrothe@vision.ee.ethz.ch Luc Van

More information

Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more

Super-Resolution. Many slides from Miki Elad Technion Yosi Rubner RTC and more Super-Resolution Many slides from Mii Elad Technion Yosi Rubner RTC and more 1 Example - Video 53 images, ratio 1:4 2 Example Surveillance 40 images ratio 1:4 3 Example Enhance Mosaics 4 5 Super-Resolution

More information

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution

Influence of Training Set and Iterative Back Projection on Example-based Super-resolution Influence of Training Set and Iterative Back Projection on Example-based Super-resolution Saeid Fazli Research Institute of Modern Biological Techniques University of zanjan Zanjan, Iran Abstract Example-based

More information

SUPPLEMENTARY MATERIAL

SUPPLEMENTARY MATERIAL SUPPLEMENTARY MATERIAL Zhiyuan Zha 1,3, Xin Liu 2, Ziheng Zhou 2, Xiaohua Huang 2, Jingang Shi 2, Zhenhong Shang 3, Lan Tang 1, Yechao Bai 1, Qiong Wang 1, Xinggan Zhang 1 1 School of Electronic Science

More information

COMPACT AND COHERENT DICTIONARY CONSTRUCTION FOR EXAMPLE-BASED SUPER-RESOLUTION

COMPACT AND COHERENT DICTIONARY CONSTRUCTION FOR EXAMPLE-BASED SUPER-RESOLUTION COMPACT AND COHERENT DICTIONARY CONSTRUCTION FOR EXAMPLE-BASED SUPER-RESOLUTION Marco Bevilacqua Aline Roumy Christine Guillemot Marie-Line Alberi Morel INRIA Rennes, Campus de Beaulieu, 35042 Rennes Cedex,

More information

Bayesian region selection for adaptive dictionary-based Super-Resolution

Bayesian region selection for adaptive dictionary-based Super-Resolution PÉREZ-PELLITERO ET AL.: BAYESIAN REGION SELECTION FOR SUPER-RESOLUTION 1 Bayesian region selection for adaptive dictionary-based Super-Resolution Eduardo Pérez-Pellitero 1, 2 eduardo.perezpellitero@technicolor.com

More information

Fast Image Super-resolution Based on In-place Example Regression

Fast Image Super-resolution Based on In-place Example Regression 2013 IEEE Conference on Computer Vision and Pattern Recognition Fast Image Super-resolution Based on In-place Example Regression Jianchao Yang, Zhe Lin, Scott Cohen Adobe Research 345 Park Avenue, San

More information

Single Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling

Single Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling Single Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling Yaniv Romano The Electrical Engineering Department Matan Protter The Computer Science Department Michael Elad The Computer Science

More information

Modeling Deformable Gradient Compositions for Single-Image Super-resolution

Modeling Deformable Gradient Compositions for Single-Image Super-resolution Modeling Deformable Gradient Compositions for Single-Image Super-resolution Yu Zhu 1, Yanning Zhang 1, Boyan Bonev 2, Alan L. Yuille 2 1 School of Computer Science, Northwestern Polytechnical University,

More information

Single Image Super-resolution using Deformable Patches

Single Image Super-resolution using Deformable Patches Single Image Super-resolution using Deformable Patches Yu Zhu 1, Yanning Zhang 1, Alan L. Yuille 2 1 School of Computer Science, Northwestern Polytechnical University, China 2 Department of Statistics,

More information

Novel Iterative Back Projection Approach

Novel Iterative Back Projection Approach IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661, p- ISSN: 2278-8727Volume 11, Issue 1 (May. - Jun. 2013), PP 65-69 Novel Iterative Back Projection Approach Patel Shreyas A. Master in

More information

Sparse Representation Based Super-Resolution Algorithm using Wavelet Domain Interpolation and Nonlocal Means

Sparse Representation Based Super-Resolution Algorithm using Wavelet Domain Interpolation and Nonlocal Means TELKOMNIKA Indonesian Journal of Electrical Engineering Vol. 16, No. 2, November 2015, pp. 296 ~ 302 DOI: 10.11591/telkomnika.v16i2.8816 296 Sparse Representation Based Super-Resolution Algorithm using

More information

ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT. Yang Xian 1 and Yingli Tian 1,2

ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT. Yang Xian 1 and Yingli Tian 1,2 ROBUST INTERNAL EXEMPLAR-BASED IMAGE ENHANCEMENT Yang Xian 1 and Yingli Tian 1,2 1 The Graduate Center, 2 The City College, The City University of New York, New York, Email: yxian@gc.cuny.edu; ytian@ccny.cuny.edu

More information

Image Restoration Using DNN

Image Restoration Using DNN Image Restoration Using DNN Hila Levi & Eran Amar Images were taken from: http://people.tuebingen.mpg.de/burger/neural_denoising/ Agenda Domain Expertise vs. End-to-End optimization Image Denoising and

More information

Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique

Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique Edge-Preserving MRI Super Resolution Using a High Frequency Regularization Technique Kaveh Ahmadi Department of EECS University of Toledo, Toledo, Ohio, USA 43606 Email: Kaveh.ahmadi@utoledo.edu Ezzatollah

More information

Introduction. Prior work BYNET: IMAGE SUPER RESOLUTION WITH A BYPASS CONNECTION NETWORK. Bjo rn Stenger. Rakuten Institute of Technology

Introduction. Prior work BYNET: IMAGE SUPER RESOLUTION WITH A BYPASS CONNECTION NETWORK. Bjo rn Stenger. Rakuten Institute of Technology BYNET: IMAGE SUPER RESOLUTION WITH A BYPASS CONNECTION NETWORK Jiu Xu Yeongnam Chae Bjo rn Stenger Rakuten Institute of Technology ABSTRACT This paper proposes a deep residual network, ByNet, for the single

More information

A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION. Jun-Jie Huang and Pier Luigi Dragotti

A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION. Jun-Jie Huang and Pier Luigi Dragotti A DEEP DICTIONARY MODEL FOR IMAGE SUPER-RESOLUTION Jun-Jie Huang and Pier Luigi Dragotti Communications and Signal Processing Group CSP), Imperial College London, UK ABSTRACT Inspired by the recent success

More information

arxiv: v1 [cs.cv] 7 Jul 2017

arxiv: v1 [cs.cv] 7 Jul 2017 A MULTI-LAYER IMAGE REPRESENTATION USING REGULARIZED RESIDUAL QUANTIZATION: APPLICATION TO COMPRESSION AND DENOISING Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov Department of Computer Science,

More information

An Optimized Pixel-Wise Weighting Approach For Patch-Based Image Denoising

An Optimized Pixel-Wise Weighting Approach For Patch-Based Image Denoising An Optimized Pixel-Wise Weighting Approach For Patch-Based Image Denoising Dr. B. R.VIKRAM M.E.,Ph.D.,MIEEE.,LMISTE, Principal of Vijay Rural Engineering College, NIZAMABAD ( Dt.) G. Chaitanya M.Tech,

More information

BSIK-SVD: A DICTIONARY-LEARNING ALGORITHM FOR BLOCK-SPARSE REPRESENTATIONS. Yongqin Zhang, Jiaying Liu, Mading Li, Zongming Guo

BSIK-SVD: A DICTIONARY-LEARNING ALGORITHM FOR BLOCK-SPARSE REPRESENTATIONS. Yongqin Zhang, Jiaying Liu, Mading Li, Zongming Guo 2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) BSIK-SVD: A DICTIONARY-LEARNING ALGORITHM FOR BLOCK-SPARSE REPRESENTATIONS Yongqin Zhang, Jiaying Liu, Mading Li, Zongming

More information

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation

A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation , pp.162-167 http://dx.doi.org/10.14257/astl.2016.138.33 A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation Liqiang Hu, Chaofeng He Shijiazhuang Tiedao University,

More information

A Comparison of Still-Image Compression Standards Using Different Image Quality Metrics and Proposed Methods for Improving Lossy Image Quality

A Comparison of Still-Image Compression Standards Using Different Image Quality Metrics and Proposed Methods for Improving Lossy Image Quality A Comparison of Still-Image Compression Standards Using Different Image Quality Metrics and Proposed Methods for Improving Lossy Image Quality Multidimensional DSP Literature Survey Eric Heinen 3/21/08

More information

IMAGE DENOISING USING NL-MEANS VIA SMOOTH PATCH ORDERING

IMAGE DENOISING USING NL-MEANS VIA SMOOTH PATCH ORDERING IMAGE DENOISING USING NL-MEANS VIA SMOOTH PATCH ORDERING Idan Ram, Michael Elad and Israel Cohen Department of Electrical Engineering Department of Computer Science Technion - Israel Institute of Technology

More information

arxiv: v2 [cs.cv] 11 Nov 2016

arxiv: v2 [cs.cv] 11 Nov 2016 Accurate Image Super-Resolution Using Very Deep Convolutional Networks Jiwon Kim, Jung Kwon Lee and Kyoung Mu Lee Department of ECE, ASRI, Seoul National University, Korea {j.kim, deruci, kyoungmu}@snu.ac.kr

More information

Compressed Sensing Algorithm for Real-Time Doppler Ultrasound Image Reconstruction

Compressed Sensing Algorithm for Real-Time Doppler Ultrasound Image Reconstruction Mathematical Modelling and Applications 2017; 2(6): 75-80 http://www.sciencepublishinggroup.com/j/mma doi: 10.11648/j.mma.20170206.14 ISSN: 2575-1786 (Print); ISSN: 2575-1794 (Online) Compressed Sensing

More information

Single Image Super-Resolution. via Internal Gradient Similarity

Single Image Super-Resolution. via Internal Gradient Similarity Single Image Super-Resolution via Internal Gradient Similarity Yang Xian and Yingli Tian * The Graduate Center and the City College of New York, City University of New York, New York, NY 10016 USA Email:

More information

Depth image super-resolution via multi-frame registration and deep learning

Depth image super-resolution via multi-frame registration and deep learning Depth image super-resolution via multi-frame registration and deep learning Ching Wei Tseng 1 and Hong-Ren Su 1 and Shang-Hong Lai 1 * and JenChi Liu 2 1 National Tsing Hua University, Hsinchu, Taiwan

More information

Locally Adaptive Learning for Translation-Variant MRF Image Priors

Locally Adaptive Learning for Translation-Variant MRF Image Priors Locally Adaptive Learning for Translation-Variant MRF Image Priors Masayuki Tanaka and Masatoshi Okutomi Tokyo Institute of Technology 2-12-1 O-okayama, Meguro-ku, Tokyo, JAPAN mtanaka@ok.ctrl.titech.ac.p,

More information

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING

IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING Jianzhou Feng Li Song Xiaog Huo Xiaokang Yang Wenjun Zhang Shanghai Digital Media Processing Transmission Key Lab, Shanghai Jiaotong University

More information

Non-local Means for Stereo Image Denoising Using Structural Similarity

Non-local Means for Stereo Image Denoising Using Structural Similarity Non-local Means for Stereo Image Denoising Using Structural Similarity Monagi H. Alkinani and Mahmoud R. El-Sakka (B) Computer Science Department, University of Western Ontario, London, ON N6A 5B7, Canada

More information

An Approach for Reduction of Rain Streaks from a Single Image

An Approach for Reduction of Rain Streaks from a Single Image An Approach for Reduction of Rain Streaks from a Single Image Vijayakumar Majjagi 1, Netravati U M 2 1 4 th Semester, M. Tech, Digital Electronics, Department of Electronics and Communication G M Institute

More information

An Improved Approach For Mixed Noise Removal In Color Images

An Improved Approach For Mixed Noise Removal In Color Images An Improved Approach For Mixed Noise Removal In Color Images Ancy Mariam Thomas 1, Dr. Deepa J 2, Rijo Sam 3 1P.G. student, College of Engineering, Chengannur, Kerala, India. 2Associate Professor, Electronics

More information

Single Image Super-Resolution

Single Image Super-Resolution Single Image Super-Resolution Abhishek Arora Dept. of Electrical Engg. Stanford University, CA Email: arorabhi@stanford.edu Ritesh Kolte Dept. of Electrical Engg. Stanford University, CA Email: rkolte@stanford.edu

More information

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION

IMAGE RECONSTRUCTION WITH SUPER RESOLUTION INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS ISSN 2320-7345 IMAGE RECONSTRUCTION WITH SUPER RESOLUTION B.Vijitha 1, K.SrilathaReddy 2 1 Asst. Professor, Department of Computer

More information

IMAGE super-resolution is the process of reconstructing

IMAGE super-resolution is the process of reconstructing 1 Adaptive Large Scale Artifact Reduction in Edge-based Image Super-Resolution Alexander Wong and William Bishop Abstract The goal of multi-frame image super-resolution is to use information from low-resolution

More information

Department of Electronics and Communication KMP College of Engineering, Perumbavoor, Kerala, India 1 2

Department of Electronics and Communication KMP College of Engineering, Perumbavoor, Kerala, India 1 2 Vol.3, Issue 3, 2015, Page.1115-1021 Effect of Anti-Forensics and Dic.TV Method for Reducing Artifact in JPEG Decompression 1 Deepthy Mohan, 2 Sreejith.H 1 PG Scholar, 2 Assistant Professor Department

More information

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter

More information

Compressed Sensing and Applications by using Dictionaries in Image Processing

Compressed Sensing and Applications by using Dictionaries in Image Processing Advances in Computational Sciences and Technology ISSN 0973-6107 Volume 10, Number 2 (2017) pp. 165-170 Research India Publications http://www.ripublication.com Compressed Sensing and Applications by using

More information

Single Image Super-Resolution Using a Deep Encoder-Decoder. Symmetrical Network with Iterative Back Projection

Single Image Super-Resolution Using a Deep Encoder-Decoder. Symmetrical Network with Iterative Back Projection Single Image Super-Resolution Using a Deep Encoder-Decoder Symmetrical Network with Iterative Back Projection Heng Liu 1, Jungong Han 2, *, Shudong Hou 1, Ling Shao 3, Yue Ruan 1 1 School of Computer Science

More information

Robust Face Recognition via Sparse Representation

Robust Face Recognition via Sparse Representation Robust Face Recognition via Sparse Representation Panqu Wang Department of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92092 pawang@ucsd.edu Can Xu Department of

More information

Structured Face Hallucination

Structured Face Hallucination 2013 IEEE Conference on Computer Vision and Pattern Recognition Structured Face Hallucination Chih-Yuan Yang Sifei Liu Ming-Hsuan Yang Electrical Engineering and Computer Science University of California

More information