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

Author(s):  
Xin Li ◽  
Jie Chen ◽  
Ziguan Cui ◽  
Minghu Wu ◽  
Xiuchang Zhu

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.

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Xuan Zhu ◽  
Xianxian Wang ◽  
Jun Wang ◽  
Peng Jin ◽  
Li Liu ◽  
...  

Sparse representation has recently attracted enormous interests in the field of image super-resolution. The sparsity-based methods usually train a pair of global dictionaries. However, only a pair of global dictionaries cannot best sparsely represent different kinds of image patches, as it neglects two most important image features: edge and direction. In this paper, we propose to train two novel pairs of Direction and Edge dictionaries for super-resolution. For single-image super-resolution, the training image patches are, respectively, divided into two clusters by two new templates representing direction and edge features. For each cluster, a pair of Direction and Edge dictionaries is learned. Sparse coding is combined with the Direction and Edge dictionaries to realize super-resolution. The above single-image super-resolution can restore the faithful high-frequency details, and the POCS is convenient for incorporating any kind of constraints or priors. Therefore, we combine the two methods to realize multiframe super-resolution. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness, and robustness of the proposed method. Experimental results demonstrate that our method can recover better edge structure and details.


2013 ◽  
Vol 457-458 ◽  
pp. 1032-1036
Author(s):  
Feng Qing Qin ◽  
Li Hong Zhu ◽  
Li Lan Cao ◽  
Wa Nan Yang

A framework is proposed to reconstruct a super resolution image from a single low resolution image with Gaussian noise. The degrading processes of Gaussian blur, down-sampling, and Gaussian noise are all considered. For the low resolution image, the Gaussian noise is reduced through Wiener filtering algorithm. For the de-noised low resolution image, iterative back projection algorithm is used to reconstruct a super resolution image. Experiments show that de-noising plays an important part in single-image super resolution reconstruction. In the super reconstructed image, the Gaussian noise is reduced effectively and the peak signal to noise ratio (PSNR) is increased.


2013 ◽  
Vol 10 (5) ◽  
pp. 50-61 ◽  
Author(s):  
Huang Wei ◽  
Xiao Liang ◽  
Wei Zhihui ◽  
Fei Xuan ◽  
Wang Kai

2011 ◽  
Vol 219-220 ◽  
pp. 1411-1414
Author(s):  
En Wei Zheng ◽  
Xian Jun Wang

In this paper, we propose a new super resolution (SR) reconstruction method to handle license plate numbers of vehicles in real traffic videos. Recently, SR reconstruction shemes based on regularization have been demonstrated to be effective because SR reconstrction is an ill-posed problem. Working within this promising framework, the residual data (RD) term can be weighted according to the differences among the observed LR images in the SR reconstruction model. Moreover, L1 norm is used to measure the RD term in order to improve the robustness of our method. Experiments show the proposed method improves the subjective visual quality of the high resolution images.


Sign in / Sign up

Export Citation Format

Share Document