Fast Single Image Super-Resolution by Self-trained Filtering (original) (raw)

Improved image super-resolution by Support Vector Regression

Support Vector Machine (SVM) can construct a hyperplane in a high or infinite dimensional space which can be used for classification. Its regression version, Support Vector Regression (SVR) has been used in various image processing tasks. In this paper, we develop an image super-resolution algorithm based on SVR. Experiments demonstrated that our proposed method with limited training samples outperforms some of the state-of-the-art approaches and during the super- resolution process the model learned by SVR is robust to reconstruct edges and fine details in various testing images. I. INTRODUCTION ith the wide spread application of video cameras, surveillance systems and hand-held devices that are equipped with moderate image sensors, it is desirable to generate images or video streams with high quality while not increasing the cost of the hardware. The imaging process of these sensors can be modeled by

Example Based Single-Frame Image Super-Resolution by Support Vector Regression

Journal of Pattern Recognition Research, 2010

As many other inverse problems, single-frame image super-resolution is an ill-posed problem. The problem has been approached in the context of machine learning. However, the proposed method in this paper is different from other learning based methods regarding how the input/output are formulated as well as how the learning is done. The assumption behind example based methods is the local similarity across seemingly different images.

Steering Kernel Regression Based Image Super resolution

Now A days Image Super-Resolution is active research topic due its widespread use in many practical application. Recently Learning-Based Approach for Super-resolution (SR) has been used which generate favorable result. In this paper image super-resolution based on the multiple kernel regression is presented. This approach's core is to learn the map between the space of high resolution image patches and the space of blurred high-resolution image patches. Which is the interpolation result generated from corresponding low-resolution image. Here using multiple kernel instead of single kernel for regression. Because choosing appropriate single kernel form image is difficult and time consuming rather than dividing image into multiple sub-band and each sub-band has own kernel. And Finally use Support Vector Regression (SVR) to fit the data in high dimensional feature space. The experimental result show that it achieve three time better quality of image than other.

Self-Learning based Single Image Super- Resolution

Images with low quality have low resolution and also have some blocking artifacts. To perform image super-resolution (SR) on this low quality image gives low visual quality of the image. In this paper a self-learning based super resolution technique is used to obtain a low quality SR on single image as well as removal of artifacts which are introduced due to compression. On the low quality image if deblocking is done, then the details may be lost. With self-learning sparse representation for low resolution and high resolution image patches by using learned dictionaries. This method gives far better results in terms of visual quality as compared with other methods of interpolation used.

Single-Image Super-Resolution via Linear Mapping of Interpolated Self-Examples

IEEE Transactions on Image Processing, 2014

This paper presents a novel example-based singleimage super-resolution (SR) procedure, that upscales to highresolution (HR) a given low-resolution (LR) input image without relying on an external dictionary of image examples. The dictionary instead is built from the LR input image itself, by generating a "double pyramid" of recursively scaled, and subsequently interpolated, images, from which self-examples are extracted. The upscaling procedure is multi-pass, i.e. the output image is constructed by means of gradual increases, and consists in learning special linear mapping functions on this double pyramid, as many as the number of patches in the current image to upscale. More precisely, for each LR patch, similar self-examples are found, and, thanks to them, a linear function is learned to directly map it into its HR version. Iterative back projection is also employed to ensure consistency at each pass of the procedure. Extensive experiments and comparisons with other state-of-theart methods, based both on external and internal dictionaries, show that our algorithm can produce visually pleasant upscalings, with sharp edges and well reconstructed details. Moreover, when considering objective metrics like PSNR and SSIM, our method turns out to give the best performance.

Multi-kernel based adaptive interpolation for image super-resolution

Multimedia Tools and Applications, 2012

This paper proposes a cost-effective and edge-directed image super-resolution scheme. Image super-resolution (image magnification) is an enthusiastic research area and is desired in a variety of applications. The basic idea of the proposed scheme is based on the concept of multi-kernel approach. Various stencils have been defined on the basis of geometrical regularities. This set of stencils is associated with the set of kernels. The value of a re-sampling pixel is obtained by calculating the weighted average of the pixels in the selected kernel. The time complexity of the proposed scheme is as low as that of classical linear interpolation techniques, but the visual quality is more appealing because of the edgeorientation property. The experimental results and analysis show that proposed scheme provides a good combination of visual quality and time complexity.

Different Implemented Techniques of Super Resolution Imaging

2015

Resolution plays a major role for interpretation and analysis of an image. Super Resolution is a technique to enhance the resolution of an image from single or multiple low resolved images, which gives detailed information present in an image. In this paper, we describe several methods for Super Resolution (SR) that enhances the quality of an image. Mainly the methods are divided into frequency domain and spatial domains. Here, we stated comparison of different approaches, challenges and issues for SR and applications of SR in practical world e.g. in medical imaging, satellite imaging, and forensics. We have approached SR using learning based techniques. We present a novel self-learning approach with multiple kernel learning for adaptive kernel selection for SR. The Multiple Kernel Learning is theoretically and technically very attractive, because it learns the kernel weights and the classifier simultaneously based on the margin criterion. With theoretical supports of kernel matching search method and Optimization approach (Gradient) are proposed our SR framework learns and selects the optimal Kernel ridge regression model when producing an SR image, which results in the minimum SR reconstruction error.

Image Interpolation by Super-Resolution

Term "super-resolution" is typically used for a high-resolution image produced from several low-resolution noisy observations. In this paper, we consider the problem of high-quality interpolation of a single noise-free image. Several aspects of the corresponding super-resolution algorithm are investigated: choice of regularization term, dependence of the result on initial approximation, convergence speed, and heuristics to facilitate convergence and improve the visual quality of the resulting image.

Modified Back Projection Kernel Based Image Super Resolution

2014 2nd International Conference on Artificial Intelligence, Modelling and Simulation, 2014

In this paper, we propose a new super resolution technique based on iterative interpolation followed by registering them using back projection (BP). Firstly the low resolution image is interpolated and then decimated to four low resolution images. The four low resolution images are interpolated and registered by using BP in order to generate a sharper high resolution image then high resolution image is down sampled and back to the first step. The proposed method has been tested on some bench mark images. The peak signal-tonoise ratio (PSNR) and structural similarity index (SSIM) results as well as the visual results shows the superiority of the proposed technique over the conventional and state-of-art image super resolution techniques. In Average, the PSNR is 2.72 dB higher than the bicubic interpolation.