Single image super-resolution using coupled dictionary learning and cross domain mapping (original) (raw)

Single Image Super-Resolution through Sparse Representation via Coupled Dictionary learning

International Journal of Electronics and Telecommunications, 2020

Abstract- Single Image Super-Resolution (SISR) through sparse representation has received much attention in the past decade due to significant development in sparse coding algorithms. However, recovering high-frequency textures is a major bottleneck of existing SISR algorithms. Considering this, dictionary learning approaches are to be utilized to extract high-frequency textures which improve SISR performance significantly. In this paper, we have proposed the SISR algorithm through sparse representation which involves learning of Low Resolution (LR) and High Resolution (HR) dictionaries simultaneously from the training set. The idea of training coupled dictionaries preserves correlation between HR and LR patches to enhance the Super-resolved image. To demonstrate the effectiveness of the proposed algorithm, a visual comparison is made with popular SISR algorithms and also quantified through quality metrics. The proposed algorithm outperforms compared to existing SISR algorithms qua...

Single image super-resolution by directionally structured coupled dictionary learning

EURASIP Journal on Image and Video Processing, 2016

In this paper, a new algorithm is proposed based on coupled dictionary learning with mapping function for the problem of single-image super-resolution. Dictionaries are designed for a set of clustered data. Data is classified into directional clusters by correlation criterion. The training data is structured into nine clusters based on correlation between the data patches and already developed directional templates. The invariance of the sparse representations is assumed for the task of super-resolution. For each cluster, a pair of high-resolution and low-resolution dictionaries are designed along with their mapping functions. This coupled dictionary learning with a mapping function helps in strengthening the invariance of sparse representation coefficients for different resolution levels. During the reconstruction phase, for a given low-resolution patch a set of directional clustered dictionaries are used, and the cluster is selected which gives the least sparse representation error. Then, a pair of dictionaries with mapping functions of that cluster are used for the high-resolution patch approximation. The proposed algorithm is compared with earlier work including the currently top-ranked super-resolution algorithm. By the proposed mechanism, the recovery of directional fine features becomes prominent.

Super Resolution and Denoising of Images via Dictionary Learning

Improving the quality of image has always been an issue of image technology. Enhancing the quality of image is a continuous ongoing process. To ensure the quality of image in image processing noise estimation and removal are very important step before analysis or using image. An example-based method for super-resolution and denoising of images is proposed. The objective is to estimate a high-resolution image from a noisy low-resolution image, with the help of a given database of high and low-resolution image patch pairs. This method uses a redundant dictionary learning to reconstruct the HR image. The redundant dictionary is trained by K-SVD algorithm which is an iterative method that alternates between sparse coding of the examples based on the current dictionary, and a process of updating the dictionary atoms to better fit the data. Denoising and super-resolution of images in this paper is performed on each image patch. In this paper K-means Singular Value Decomposition (K-SVD) and Iterative Back Projection methods are proposed for denoising and Super Resolution of images. These algorithms significantly improve the resolution and eliminate the blur and noise associated with low resolution images, when compared with the other existing methods.

Super resolution image reconstruction via dual dictionary learning in sparse environment

International Journal of Electrical and Computer Engineering (IJECE)

Patch-based super resolution is a method in which spatial features from a low-resolution (LR) patch are used as references for the reconstruction of high-resolution (HR) image patches. Sparse representation for each patch is extracted. These coefficients obtained are used to recover HR patch. One dictionary is trained for LR image patches, and another dictionary is trained for HR image patches and both dictionaries are jointly trained. In the proposed method, high frequency (HF) details required are treated as combination of main high frequency (MHF) and residual high frequency (RHF). Hence, dual-dictionary learning is proposed for main dictionary learning and residual dictionary learning. This is required to recover MHF and RHF respectively for recovering finer image details. Experiments are carried out to test the proposed technique on different test images. The results illustrate the efficacy of the proposed algorithm.

Sparse Representation Based Single Image Dictionary Construction For Image Super Resolution

2015

Sparse representation-linear combination of very few elements which are represented in vector format called as atoms. Dictionary-specific data set is formed to reconstruct the signal. Generally dictionary can be trained in two ways (i) Based on sparse mathematical model (ii) learning a dictionary based on training set or external images. In this paper a new Super Resolution (SR) approach is employed for underwater side scan sonar image. The SR technique exploits dictionary based sparse representation model. In order to extemporaneously construct an over-complete dictionary from a single image a new algorithm is proposed. Proposed approach improves performance through joint combinatorial optimization of sparse coefficients and Dictionary. In proposed super resolution technique efficiency is measured using various performance metrics like peak signal to noise ratio (PSNR) and structural similarity index measurement (SSIM). Proposed technique of super resolution further reduces the computational time.

Image Super-Resolution Reconstruction Based On Multi-Dictionary Learning

In order to overcome the problems that the single dictionary cannot be adapted to variety types of images and the reconstruction quality couldn't meet the application, we propose a novel Multi-Dictionary Learning algorithm for feature classification. The algorithm uses the orientation information of the low resolution image to guide the image patches in the database to classify, and designs the classification dictionary which can effectively express the reconstructed image patches. Considering the nonlocal similarity of the image, we construct the combined nonlocal mean value(C-NLM) regularizer, and take the steering kernel regression(SKR) to formulate a local regularization ,and establish a unified reconstruction framework. Extensive experiments on single image validate that the proposed method, compared with several other state-of-the-art learning based algorithms, achieves improvement in image quality and provides more details.

Convolutional Sparse Coding Using Wavelets for Single Image Super-Resolution

IEEE Access, 2019

In this paper, we propose the convolutional sparse coding based model in the wavelet domain for the task of single image super-resolution (SISR). The conventional sparse coding based approaches work on overlapping image patches and use the dictionary atoms to sparse code an image patch. Further, at the final stage, an overlap-add mechanism is used to get the final high-resolution image estimate. However, these algorithms fail to take into account the consistency present in the overlapping patches which limits their performance. We propose the use of wavelet integrated convolutional sparse coding approach where instead of dictionary atoms we utilize the convolution summations between the learned filters and their mappings for sparse representation based SISR. The use of wavelets is proposed owing to their unique directional and compact features. A pair of filters are learned along with a mapping function for each wavelet sub-band to exploit the consistency among patches. The proposed wavelet integrated convolutional sparse coding model helps capture useful contextual information. The proposed model is evaluated on publicly available datasets for different scale-up parameters. To show the efficacy of the proposed model we compare it with recent state-of-the-art algorithms. The visual results along with the quantitative ones indicate that the proposed model performs well for the tasks of super-resolution.

Image Super-Resolution Via Sparse Representation

IEEE Transactions on Image Processing, 2000

This paper presents a new approach to single-image superresolution, based on sparse signal representation. Research on image statistics suggests that image patches can be wellrepresented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary. Inspired by this observation, we seek a sparse representation for each patch of the low-resolution input, and then use the coefficients of this representation to generate the high-resolution output. Theoretical results from compressed sensing suggest that under mild conditions, the sparse representation can be correctly recovered from the downsampled signals. By jointly training two dictionaries for the low-and high-resolution image patches, we can enforce the similarity of sparse representations between the low resolution and high resolution image patch pair with respect to their own dictionaries. Therefore, the sparse representation of a low resolution image patch can be applied with the high resolution image patch dictionary to generate a high resolution image patch. The learned dictionary pair is a more compact representation of the patch pairs, compared to previous approaches, which simply sample a large amount of image patch pairs [1], reducing the computational cost substantially. The effectiveness of such a sparsity prior is demonstrated for both general image superresolution and the special case of face hallucination. In both cases, our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. In addition, the local sparse modeling of our approach is naturally robust to noise, and therefore the proposed algorithm can handle super-resolution with noisy inputs in a more unified framework.

Image Super-Resolution Reconstruction Using Adaptive Co-sparse Regularization with Dual Dictionary

International Journal of Modeling and Optimization, 2016

This paper present a new method based on co-sparse with learning paired dictionary. The new framework is consisted of three parts. Firstly a paired dictionary have been learned which is used to overcome a low resolution image by utilizing an externally applied high resolution (HR) dictionary and then learn based on the internal dictionary. Process the paired dictionary which consists of low resolution (LR) and high resolution (HR) dictionary by kernel regression based on their coefficient respectively, and applied directly to construct the HR patches. Secondly, co-sparse regularization and features of self similarity have been introduced to strengthen and enhanced the image structure. In addition, propagation filtering is applied to suppress the artefacts generated from neighboring pixel of an image while reserving the image edges. Finally, the HR image is generated by reconstructing all superior HR patches. The effectiveness of the co-sparse demonstrated in real test images. The proposed method achieved good quality high resolution images that are superior compared with different SR methods in terms of peak signal to noise ratio (PSNR), and structural similarity (SSIM).

Super-Resolution Image Reconstruction with Improved Sparse Representation

International Journal of Software Engineering and Its Applications

In this paper, we present a new approach to reconstruct a high resolution (HR) image from a low resolution (LR) input image based on a two dimensional (2D) sparse method. The new method consists of three phases. Firstly, the nonlinear feature of the input LR image is divided into the linear subspace, and then LR-HR dictionaries are learned to reduce the blurred artifacts of the image. Secondly, 2D sparse representation and selfsimilarity are developed to strengthen and enhance the image structure. Finally, the final HR image is achieved by reconstruction of all HR patches. Simulation results demonstrated that our proposed method achieved superior results on real images, and shows various improvements in terms of PSNR and SSIM values as compared with some other competent methods.