Super Resolution and Denoising of Images via Dictionary Learning

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.

IJRTE, 2019

Digital image processing uses efficient computer algorithms for image denoising and to improve the image quality. Noisy image is produced due to various reasons in image acquisition, compression, preprocessing, segmentation etc. Over the last decade, various methods have shown promising results in removing zero mean Gaussian noise from images. Apart from different strategies implemented for noise reduction; this paper proposes a method for reducing noise and to improve metric parameters. Without using pre-chosen set of basis functions to represent the image, this paper discuss about performing image denoising using dictionary learning and sparse representation. Instead of removing coefficients of noise, shrinking sparse coefficients of noise is implemented to eliminate noise and it retains the image quality

Multimedia Tools and Applications, 2017

In this paper, a new algorithm for single image super resolution using coupled wavelet and spatial domain dictionary pairs is proposed. The standard deviation parameter, which is approximately scale invariant for low and high resolution patch pairs is employed for clustering. A pair of online coupled dictionaries is learned for each cluster using a low resolution image. The standard deviation measure of a low resolution patch is used to select the appropriate cluster dictionary pair for reconstructing the high resolution counterpart. Experimental results show that the performance of the proposed algorithm is superior to the existing methods in terms of objective and subjective quality measures. The objective image quality is measured in terms of PSNR and SSIM. This paper also proposed an extended algorithm, based on selective sparse representation over a set of coupled dictionary pair. The extended algorithm applies the coupled dictionary based sparse framework for patches having high standard deviation. Whereas, low complexity patch collaging method is used to super resolve low standard deviation valued patches. It is found empirically that a large percentage of patches have low standard deviation values. Moreover, the selective approach significantly reduces the computational complexity without losing the overall reconstruction quality.

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.

Symmetry, 2018

We proposed a new efficient image denoising scheme, which leads to four important contributions. The first is to integrate both reconstruction and learning based approaches into a single model so that we are able to benefit advantages from both approaches simultaneously. The second is to handle both multiplicative and additive noise removal problems. The third is that the proposed approach introduces a sparse term to reduce non-Gaussian outliers from multiplicative noise and uses a Laplacian Schatten norm to capture the global structure information. In addition, the image is represented by preserving the intrinsic local similarity via a sparse coding method, which allows our model to incorporate both global and local information from the image. Finally, we propose a new method that combines Method of Optimal Directions (MOD) with Approximate K-SVD (AK-SVD) for dictionary learning. Extensive experimental results show that the proposed scheme is competitive against some of the state-of-the-art denoising algorithms.

Super-resolution (SR) image reconstruction is the signal processing technique of fusing many low resolution images into a single higher resolution image. A sparse parameter dictionary framework for super-resolution image reconstruction is proposed, which amalgamates the feature patches of high resolution and low-resolution images using sparse parameter dictionary coding. This technique fabricates a sparse connection between middle-frequency and high-frequency image elements and comprehends concurrently match searching and optimization methods. Comparison with sparse coding method shows sparse parameter dictionary is more dense and efficient. Sparse Kernel-Single Value Decomposition algorithm is applied for optimization to fasten the sparse coding process. Few experiments with real images depict that sparse parameter dictionary coding surpasses all other learning-based super-resolution algorithms in terms of PSNR.

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).

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 based on Compressed Sensing (CS) considers low resolution (LR) image patch as the compressive measurement of its corresponding high resolution (HR) patch. In this paper we propose a single image super resolution scheme with compressive K-SVD algorithm(CKSVD) for dictionary learning incorporating fusion of sparse approximation algorithms to produce better results. The CKSVD algorithm is able to learn a dictionary on a set of training signals using only compressive sensing measurements of them. In the fusion based scheme used for sparse approximation, several CS reconstruction algorithms participate and they are executed in parallel, independently. The final estimate of the underlying sparse signal is derived by fusing the estimates obtained from the participating algorithms. The experimental results show that the proposed scheme demands fewer CS measurements for creating better quality super resolved images in terms of both PSNR and visual perception.

Noise suppression from image is a still a big challenging problem for researchers. Image may be corrupted during the transmission or storage time, so removing the noise from the processed image and should preserve the important information. In this paper image patch is representing as sparse code. We are selecting the sparse code from the complete dictionary which is linear group of few atoms. By the addition of sparse coding noise to image we can enhance the performance of sparse representation. Here by restoring the image reducing the sparse coding noise in this paper we are adopting the method of adding the sparse coding noise. For getting of high resolution output the sparse coding noise should be least amount with high PSNR.