Filters








2,683 Hits in 8.6 sec

Super-resolution via K-means sparse coding

Yi Tang, Qi Wang
2013 2013 International Conference on Wavelet Analysis and Pattern Recognition  
Dictionary learning and sparse representation are efficient methods for single-image super-resolution.  ...  We propose a new approach to learn a set of dictionaries and then choose the suitable one for a given test image patch of low resolution.  ...  In this paper, we propose a novel super-resolution method based on K-means-sparse coding. In order to adaptively select the most suitable dictionary, K-means method is utilized.  ... 
doi:10.1109/icwapr.2013.6599331 fatcat:h62q4frgprcwzomx4o7qwgwgwm

Image Super-Resolution Reconstruction based on Multi-Groups of Coupled Dictionary and Alternative Learning

Sun Guangling, Li Guoqing, Jiang Xiaoqing
2012 International Journal of Computer Applications  
A novel image super-resolution reconstruction framework based on multi-groups of coupled dictionary and alternative learning is investigated in this paper.  ...  Then sparse representations and corresponding errors are calculated for each patch of the LRI by using low resolution component of each group of coupled dictionary.  ...  Recently, sparse representation and dictionary learning have become one of the most important tools to address a wide range of image processing problems including super resolution.  ... 
doi:10.5120/5577-7683 fatcat:ev3ixel45jgzzjdrder25gjhgy

Enhancing face recognition at a distance using super resolution

Nadia AL-Hassan, Sabah A. Jassim, Harin Sellahewa
2012 Proceedings of the on Multimedia and security - MM&Sec '12  
In this paper, we propose an alternative super resolution scheme based on dictionaries in high frequency wavelet subbands.  ...  The first method is based on pairs of high and low quality dictionaries in the spatial domain and the other method is the so called Back-Project Iterative Interpolation for super resolution.  ...  The computed sparse representation adaptively selects the most relevant patch bases in the dictionary to best represent each patch of the given low-resolution image.  ... 
doi:10.1145/2361407.2361429 dblp:conf/mmsec/Al-HassanJS12 fatcat:wvsupm75u5efxdhpx2npio27z4

Remote Sensing Image Super-resolution Based on Sparse Representation

Fuzhen Zhu, Yue Liu, Xin Huang, Haitao Zhu, Yansong Wang
2018 MATEC Web of Conferences  
In order to obtain higher resolution remote sensing images with more details, an improved sparse representation remote sensing image super-resolution reconstruction(SRR) algorithm is proposed.  ...  Experiment results show that, compared with the most advanced sparse representation superresolution algorithm, the improved sparse representation super-resolution method can effectively avoid the loss  ...  Comparing remote sensing image SRR results with different algorithms, experiments shows that result of the improved sparse representation image super-resolution reconstruction has clearer visual effects  ... 
doi:10.1051/matecconf/201823202037 fatcat:delakdurkbgq5p2jocmvzhy664

Single Image Super-Resolution - A Quantitative Comparison

Lisha P P, Jayasree V K
2015 International Journal of Engineering Research and  
From the analysis we have found that learning based algorithm using sparse dictionary performs better.  ...  Super-resolution (SR) techniques generates high resolution (HR) image from low resolution (LR) images.  ...  This algorithm uses single image superresolution based on self-example learning and sparse representation.  ... 
doi:10.17577/ijertv4is050888 fatcat:65vgcn5xkzckxdbqbozfsqv6ma

Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

Weisheng Dong, Lei Zhang, Guangming Shi, Xiaolin Wu
2011 IEEE Transactions on Image Processing  
Extensive experiments on image deblurring and super-resolution validate that by using adaptive sparse domain selection and adaptive regularization, the proposed method achieves much better results than  ...  patches, and then for a given patch to be processed, one set of bases are adaptively selected to characterize the local sparse domain.  ...  CONCLUSION We proposed a novel sparse representation-based image deblurring and (single-image) super-resolution method using adaptive sparse domain selection (ASDS) and adaptive regularization (AReg).  ... 
doi:10.1109/tip.2011.2108306 pmid:21278019 fatcat:kruc7xhp5be2bgc4ci52wnnk64

Realizing the Effective Detection of Tumor in Magnetic Resonance Imaging using Cluster-Sparse Assisted Super-Resolution

Kathiravan Srinivasan, Ramaneswaran Selvakumar, Sivakumar Rajagopal, Dimiter Georgiev Velev, Branislav Vuksanovic
2021 Open Biomedical Engineering Journal  
This SR method effectively captures similarity in non-locally positioned patches by training on clusters of patches using a self-adaptive dictionary.  ...  To exploit the non-local self-similarity and intrinsic sparsity in MR images, this paper proposes the use of Cluster-Sparse Assisted Super-Resolution.  ...  An iterative algorithm based on Split Bregman method coupled with self-adaptive cluster dictionary learning method is used for image restoration.  ... 
doi:10.2174/1874120702115010170 fatcat:v7gh4svtkzdbrfkslqobt5aeqy

Super resolution reconstruction of image gradient profile sharpness

2016 International Journal of Latest Trends in Engineering and Technology  
[4] proposed a novel coupled dictionary training method for single-image super-resolution (SR) based on patch wise sparse recovery, where learned couple dictionaries are relate the low and high resolution  ...  PROPOSED WORK Image super resolution algorithm is proposed based on gradient profile sharpness (GPS) and Profile Dictionary.  ... 
doi:10.21172/1.81.042 fatcat:jseuv2edezfqpdkyh5qcc7ltxi

Image Super-Resolution Based on Sparse Coding with Multi-Class Dictionaries

Xiuxiu Liao, Kejia Bai, Qian Zhang, Xiping Jia, Shaopeng Liu, Jin Zhan
2019 Computing and informatics  
Sparse coding-based single image super-resolution has attracted much interest.  ...  In this paper, a super-resolution reconstruction algorithm based on sparse coding with multi-class dictionaries is put forward.  ...  Rahiman and George [9] propose learning-based approaches for single image super-resolution using sparse representation and neighbor embedding.  ... 
doi:10.31577/cai_2019_6_1301 fatcat:t33wxsnnwfbujlrl6mbmtyfqvm

Single image super resolution based on sparse representation via directionally structured dictionaries

Fahime Farhadifard, Elham Abar, Mahmoud Nazzal, Huseyin Ozkaramanh
2014 2014 22nd Signal Processing and Communications Applications Conference (SIU)  
In this thesis, we propose an algorithm of sparse representation using structurally directional dictionaries to super resolve a single low resolution input image.  ...  Furthermore, designing multiple dictionaries with smaller sizes leads to less computational complexity. The proposed algorithm is based on dictionary learning in the spatial domain.  ...  SUPER RESOLUTION VIA SPARSE REPRESENTATION Introduction Obtaining a high-resolution (HR) image from the single low-resolution (LR) image is known as "single image super-resolution (SISR)".  ... 
doi:10.1109/siu.2014.6830580 dblp:conf/siu/FarhadifardANO14 fatcat:d27w235al5a3pedfpftjbtz76i

Single image super-resolution using sparse representations with structure constraints

J. C. Ferreira, O. Le Meur, C. Guillemot, E. A. B. da Silva, G. A. Carrijo
2014 2014 IEEE International Conference on Image Processing (ICIP)  
This paper describes a new single-image super-resolution algorithm based on sparse representations with image structure constraints.  ...  The proposed method, named Sharper Edges based Adaptive Sparse Domain Selection (SE-ASDS), achieves much better results than many stateof-the-art algorithms, showing significant improvements in terms of  ...  SUPER-RESOLUTION USING SPARSE REPRESENTATIONS: BACKGROUND Sparsity has been used in different single-image SR algorithms, particularly in learning-based methods.  ... 
doi:10.1109/icip.2014.7025784 dblp:conf/icip/FerreiraMGSC14 fatcat:nyaschml3nfslorh4rb63xhfc4

Bayesian region selection for adaptive dictionary-based Super-Resolution

Eduardo Pérez-Pellitero, Jordi Salvador, Javier Ruiz-Hidalgo, Bodo Rosenhahn
2013 Procedings of the British Machine Vision Conference 2013  
The performance of dictionary-based super-resolution (SR) strongly depends on the contents of the training dataset.  ...  Trained with this adapted subset of patches, sparse coding SR is applied to recover the high-resolution image.  ...  This paper proposes a novel sparse SR method, which focuses on adaptively selecting optimal patches for the dictionary training.  ... 
doi:10.5244/c.27.37 dblp:conf/bmvc/Perez-PelliteroSHR13 fatcat:74janxr3ljdk7nc4cqprqvsy5u

Image super-resolution as sparse representation of raw image patches

Jianchao Yang, John Wright, Thomas Huang, Yi Ma
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
The low-resolution image is viewed as downsampled version of a high-resolution image, whose patches are assumed to have a sparse representation with respect to an over-complete dictionary of prototype  ...  representation is sparse and the recovered high-resolution image is competitive or even superior in quality to images produced by other SR methods.  ...  Section 2 details our formulation and solution to the image super-resolution problem based on sparse representation.  ... 
doi:10.1109/cvpr.2008.4587647 dblp:conf/cvpr/YangWHM08 fatcat:crpeh7lwxvfgnjud3z2fbkfrwm

A New Integrated Approach Based on the Iterative Super-Resolution Algorithm and Expectation Maximization for Face Hallucination

K. Lakshminarayanan, R. Santhana Krishnan, E. Golden Julie, Y. Harold Robinson, Raghvendra Kumar, Le Hoang Son, Trinh Xuan Hung, Pijush Samui, Phuong Thao Thi Ngo, Dieu Tien Bui
2020 Applied Sciences  
This paper proposed and verified a new integrated approach based on the iterative super-resolution algorithm and expectation-maximization for face hallucination, which is a process of converting a low-resolution  ...  The current sparse representation for super resolving generic image patches is not suitable for global face images due to its lower accuracy and time-consumption.  ...  An advantage of the learning-based approach is its ability to reconstruct the HR image from the single LR image. Learning-based super-resolution is applied to human facial images [14] .  ... 
doi:10.3390/app10020718 fatcat:g3hdzjiv5jhazednwyfqf4y4ua

Face Recognition from Degraded Images – Super Resolution Approach by Non-adaptive Image-Independent Compressive Sensing Dictionaries [chapter]

Sabah A. Jassim
2013 Lecture Notes in Computer Science  
These results demonstrate that non-adaptive image-independent implicitly designed dictionaries that guarantee the recovery of sparse signals achieve face recognition accuracy levels and yield significant  ...  We present the results of our recent investigations 1 into the construction of over-complete dictionaries that recover super-resolved face images from any input low-resolution degraded face image.  ...  In order to recover super resolved image from a single LR image for face recognition via sparse representation, two overcomplete dictionaries , of size 25 512 and 100 512 respectively have been generated  ... 
doi:10.1007/978-3-642-40779-6_22 fatcat:kjg5n36gy5hv7lznwwcb5vngpm
« Previous Showing results 1 — 15 out of 2,683 results