A survey of Super resolution Techniques

Journal of Advanced Computer Science and Technology, 2018

The image resolution is probably the primary measurements of the image quality. The image with higher resolution is required and generally desired in the majority of applications, because of it represents the additional information inside the image. However, the best using of image sensors and optical technologies is normally a high priced and also restrictive method to increase the image pixel density. Therefore, the effective use of image processing techniques for acquiring a high-resolution image generated from low-resolution images is an inexpensive and a powerful solution. This kind of image improvement is termed super-resolution image. Numerous strategies like frequency domain, interpolation, and regularization techniques are proposed for generating the super resolution image. In this paper, a general survey of the available multi-frame super resolution approaches is explained. Finally, several image quality metrics are discussed to measure the similarity between the reconstructed image and the original image.

IEEE, 2018

One of the primary measurements of image quality is image resolution. High-resolution images are often required and desired for most of applications as they embody supplementary information. However, the best utilization of image sensors and optical technologies to increase the image pixel density is usually restrictive and overpriced. Therefore, the effective use of image processing techniques for acquiring a high-resolution image generated from low-resolution images is an inexpensive and powerful solution. This kind of image improvement is named image super-resolution. This paper undertakes to investigate the current super-resolution approaches adopted to generate a highresolution image. Furthermore, it highlights the strengths and the limitations of these approaches. More to the point, several image quality metrics are discussed to measure the similarity between the reconstructed image and the original image.

Theoretical and practical limitations usually constrain the achievable resolution of any imaging device. Super-Resolution (SR) methods are developed through the years to go beyond this limit by acquiring and fusing several low-resolution (LR) images of the same scene, producing a high-resolution (HR) image. The early works on SR, although occasionally mathematically optimal for particular models of data and noise, produced poor results when applied to real images. In this paper, we discuss two of the main issues related to designing a practical SR system, namely reconstruction accuracy and computational efficiency. Reconstruction accuracy refers to the problem of designing a robust SR method applicable to images from different imaging systems. We study a general framework for optimal reconstruction of images from grayscale, color, or color filtered (CFA) cameras. The performance of our proposed method is boosted by using powerful priors and is robust to both measurement (e.g. CCD re...

The matter of Resolution Enhancement has become one of the most important Electronic and Dig ital processing applications in the last few decades. Super Resolution is one of the techniques used for Resolution Enhancement. Super resolution techniques are used to provide higher resolution of an image without distorting an image. Super resolution can be done using two ways: Single frame and Multi frame. For the former directly an interpolation technique can be applied to get a high resolution image fro m a lo w resolution image and for later mu ltiple low resolutions images can be combined to form a h igh resolution image. Using this techniques resolution of any digital or electronic system can be enhanced. This paper addresses the matter of image super-resolution, which is the strategy by which one or more lo w-resolution images are processed together to create an image of high quality or set of images with a higher spatial resolution. Multi-frame image super-resolution refers to the particular case where mu ltip le images of the spot are available. Iterati ve B ack projecti on, Projecti on onto convex sets (POCS)

In this paper, we summary about the different research papers that applicable to our topic of Research which mentioned above. Image Super Resolution is a most important subject of research in the area of Image Processing. The "super resolution image" refers as technique to produce the high resolution of image from single or multiple low resolution images. The basically idea for Super-Resolution (SR) is that the fusion of a sequence of low-resolution (LR) which are noisy and blurred images that create a higher resolution (HR) image. For super resolution which is process of restoring and de noising of image. Types of resolution methods have been used so far can be divided into three groups as frequency-domain methods, spatial domain methods and techniques can be classified as the wavelet domain.

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.

2016

Image reconstruction techniques are used to create a two dimensional and three dimensional images. For image reconstruction different methods are used such as back projection filters. Image reconstruction is commonly referd to as restoration of missing parts. Super-resolution technique aims to increase the resolution of the limits of the original image or video. It is used to extract the lost details of an image when it was up scaled. Interpolation based SR, Example based SR and Multi image based SR are the main techniques for reconstructing a super resolution image from LR image. Resolution refers to denote the number of pixels in an image and it is measured in pixel Per Inch (PPI). SR technique reduces the image’s blurring and used in many image processing applications. SR technique applied in an improvement of test images, compressed video and image enhancement, medical imaging process and satellite and aerial imaging. SR is a badly postured issue on the grounds that every LR pix...

Super Resolution (SR) is an image reconstruction process in which the resolution of an image is improved. It searches for creating a high quality image from combining one or more low quality images.

A brief introduction to spatial-domain Super-Resolution methods, i.e. spatial resolution enhancement methods that create one high-resolution image from a series of low-resolution images shifted by a sub-pixel distance, is given. An improvement applicable to some of existing Super-Resolution methods is presented. Principles of digital photography processing techniques are exploited in order to reduce error in the Super-Resolution process. Enhanced registration method applicable to full color images is proposed and results of its hardware implementation are presented.

Improving image quality has always been an issue of image technology. Enhancing the quality of image is a continuous ongoing process. For some applications it becomes essential to have best quality of image such as in forensic department, where in order to retrieve maximum possible information image has to be enlarged in terms of size. For example sometimes in forensic investigations either criminal face or in video surveillance a licences number plate, increased image size helps to extract minute information embedded in the image. During this exercise beyond a certain limit, the enlarged image results in a blurred picture. Most possible cause of this problem is the hardware limitation, primarily which includes the sampling rate of a Charge- Coupled Device [CCD]. Especially this becomes very critical while capturing a high speed moving object. In such case pre/post-image processing is required which in turn restores the High resolution (HR) / Super resolution (SR) image(s) from the captured low resolution (LR) image(s). Such obtained high quality images have also a concern in satellite imaging, medical science, high Definition Television (HD TV), etc. There are various techniques to attain an image with higher resolution. In this paper some of the approaches of super resolution are discussed.