A New Super-Resolution Reconstruction Algorithm Based on Block Sparse Representation

2013 ◽  
Vol 710 ◽  
pp. 603-607
Author(s):  
Xiao Dong Zhao ◽  
Jian Zhong Cao ◽  
Hui Zhang ◽  
Guang Sen Liu ◽  
Hua Wang ◽  
...  
Keyword(s):  
Sparse Representation ◽  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Training Data ◽  
Self Similarity ◽  
Image Block ◽  
Non Local ◽  
Simulation Results ◽  
Sr Reconstruction ◽  
Suppress Noise

In this paper, we propose a new single super-resolution (SR) reconstruction algorithm via block sparse representation and regularization constraint. Firstly, discrete K-L transform is used to learn compression sub-dictionary according to the specific image block. Combined with threshold choice of training data, the transform bases are generated adaptively corresponding to the sparse domain. Secondly, Non-local Self-similarity (NLSS) regularization term is introduced into sparse reconstruction objective function as a prior knowledge to optimize reconstruction result. Simulation results validate that the proposed algorithm achieves much better results in PSNR and SSIM. It can both enhance edge and suppress noise effectively, which proves better robustness.

scholarly journals Super-resolution reconstruction for a single image based on self-similarity and compressed sensing

2018 ◽  
Vol 12 (3) ◽  
pp. 234-244
Author(s):  
Qiang Yang ◽  
Huajun Wang
Keyword(s):  
Image Reconstruction ◽  
Compressed Sensing ◽  
Sparse Representation ◽  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Single Image ◽  
Low Resolution ◽  
Self Similarity ◽  
Resolution Image ◽  
Reconstruction Performance

Super-resolution image reconstruction can achieve favorable feature extraction and image analysis. This study first investigated the image’s self-similarity and constructed high-resolution and low-resolution learning dictionaries; then, based on sparse representation and reconstruction algorithm in compressed sensing theory, super-resolution reconstruction (SRSR) of a single image was realized. The proposed algorithm adopted improved K-SVD algorithm for sample training and learning dictionary construction; additionally, the matching pursuit algorithm was improved for achieving single-image SRSR based on image’s self-similarity and compressed sensing. The experimental results reveal that the proposed reconstruction algorithm shows better visual effect and image quality than the degraded low-resolution image; moreover, compared with the reconstructed images using bilinear interpolation and sparse-representation-based algorithms, the reconstructed image using the proposed algorithm has a higher PSNR value and thus exhibits more favorable super-resolution image reconstruction performance.

scholarly journals Image Super-Resolution via Self-Similarity Learning and Conformal Sparse Representation

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 68277-68287 ◽  
Author(s):  
Shiyan Wang ◽  
Yaoyao Wei ◽  
Ken Long ◽  
Xi Zeng ◽  
Min Zheng
Keyword(s):  
Sparse Representation ◽  
Super Resolution ◽  
Similarity Learning ◽  
Self Similarity ◽  
Image Super Resolution

Multi-Frame Super-Resolution Reconstruction Algorithm Based on Diffusion Tensor Regularization Term

2014 ◽  
Vol 543-547 ◽  
pp. 2828-2832 ◽  
Author(s):  
Xiao Dong Zhao ◽  
Zuo Feng Zhou ◽  
Jian Zhong Cao ◽  
Long Ren ◽  
Guang Sen Liu ◽  
...  
Keyword(s):  
Diffusion Tensor ◽  
Lagrange Equation ◽  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Energy Functional ◽  
L1 Norm ◽  
Regularization Term ◽  
Sr Reconstruction ◽  
Image Edges ◽  
Anisotropic Diffusion Equation

This paper presents a multi-frame super-resolution (SR) reconstruction algorithm based on diffusion tensor regularization term. Firstly, L1-norm structure is used as data fidelity term, anisotropic diffusion equation with directional smooth characteristics is introduced as a prior knowledge to optimize reconstruction result. Secondly, combined with shock filter, SR reconstruction energy functional is established. Finally, Euler-Lagrange equation based on nonlinear diffusion model is exported. Simulation results validate that the proposed algorithm enhances image edges and suppresses noise effectively, which proves better robustness.

scholarly journals Fusion of Hyperspectral and Multispectral Images Based on a Centralized Non-local Sparsity Model of Abundance Maps

Tecnura ◽  
2020 ◽  
Vol 24 (66) ◽  
pp. 62-75
Author(s):  
Edwin Vargas ◽  
Kevin Arias ◽  
Fernando Rojas ◽  
Henry Arguello
Keyword(s):  
Image Fusion ◽  
Sparse Representation ◽  
Spatial Resolution ◽  
Real Data ◽  
Spectral Unmixing ◽  
Multispectral Images ◽  
Self Similarity ◽  
Diverse Range ◽  
Learned Dictionary ◽  
Non Local

Objective: Hyperspectral (HS) imaging systems are commonly used in a diverse range of applications that involve detection and classification tasks. However, the low spatial resolution of hyperspectral images may limit the performance of the involved tasks in such applications. In the last years, fusing the information of an HS image with high spatial resolution multispectral (MS) or panchromatic (PAN) images has been widely studied to enhance the spatial resolution. Image fusion has been formulated as an inverse problem whose solution is an HS image which assumed to be sparse in an analytic or learned dictionary. This work proposes a non-local centralized sparse representation model on a set of learned dictionaries in order to regularize the conventional fusion problem.Methodology: The dictionaries are learned from the estimated abundance data taking advantage of the depth correlation between abundance maps and the non-local self- similarity over the spatial domain. Then, conditionally on these dictionaries, the fusion problem is solved by an alternating iterative numerical algorithm.Results: Experimental results with real data show that the proposed method outperforms the state-of-the-art methods under different quantitative assessments.Conclusions: In this work, we propose a hyperspectral and multispectral image fusion method based on a non-local centralized sparse representation on abundance maps. This model allows us to include the non-local redundancy of abundance maps in the fusion problem using spectral unmixing and improve the performance of the sparsity-based fusion approaches.

Single Image Super-Resolution Based on Sparse Representation with Adaptive Dictionary Selection

2016 ◽  
Vol 30 (07) ◽  
pp. 1654006 ◽  
Author(s):  
Xin Li ◽  
Jie Chen ◽  
Ziguan Cui ◽  
Minghu Wu ◽  
Xiuchang Zhu
Keyword(s):  
Sparse Representation ◽  
Super Resolution ◽  
Computation Time ◽  
Resolution Image ◽  
Image Patches ◽  
Different Types ◽  
Image Super Resolution ◽  
Sr Reconstruction ◽  
Single Image Super Resolution

Sparse representation theory has attracted much attention, and has been successfully used in image super-resolution (SR) reconstruction. However, it could only provide the local prior of image patches. Field of experts (FoE) is a way to develop the generic and expressive prior of the whole image. The algorithm proposed in this paper uses the FoE model as the global constraint of SR reconstruction problem to pre-process the low-resolution image. Since a single dictionary could not accurately represent different types of image patches, our algorithm classifies the sample patches composed of pre-processed image and high-resolution image, obtains the sub-dictionaries by training, and adaptively selects the most appropriate sub-dictionary for reconstruction according to the pyramid histogram of oriented gradients feature of image patches. Furthermore, in order to reduce the computational complexity, our algorithm makes use of edge detection, and only applies SR reconstruction based on sparse representation to the edge patches of the test image. Nonedge patches are directly replaced by the pre-processing results of FoE model. Experimental results show that our algorithm can effectively guarantee the quality of the reconstructed image, and reduce the computation time to a certain extent.

scholarly journals Hyperspectral Image Super-Resolution via Adaptive Dictionary Learning and Double l1 Constraint

2019 ◽  
Vol 11 (23) ◽  
pp. 2809 ◽  
Author(s):  
Tang ◽  
Xu ◽  
Huang ◽  
Huang ◽  
Sun
Keyword(s):  
Sparse Representation ◽  
Spatial Resolution ◽  
Quality Evaluation ◽  
Hyperspectral Image ◽  
High Spatial Resolution ◽  
Super Resolution ◽  
Training Data ◽  
Evaluation Indexes ◽  
Image Super Resolution ◽  
The Relationship

Hyperspectral image (HSI) super-resolution (SR) is an important technique for improving the spatial resolution of HSI. Recently, a method based on sparse representation improved the performance of HSI SR significantly. However, the spectral dictionary was learned under a fixed size, empirically, without considering the training data. Moreover, most of the existing methods fail to explore the relationship among the sparse coefficients. To address these crucial issues, an effective method for HSI SR is proposed in this paper. First, a spectral dictionary is learned, which can adaptively estimate a suitable size according to the input HSI without any prior information. Then, the proposed method exploits the nonlocal correlation of the sparse coefficients. Doubleregularized sparse representation is then introduced to achieve better reconstructions for HSI SR. Finally, a high spatial resolution HSI is generated by the obtained coefficients matrix and the learned adaptive size spectral dictionary. To evaluate the performance of the proposed method, we conduct experiments on two famous datasets. The experimental results demonstrate that it can outperform some relatively state-of-the-art methods in terms of the popular universal quality evaluation indexes.

Sign in / Sign up

Export Citation Format

Share Document