SINGLE IMAGE SUPER RESOLUTION: A COMPARATIVE STUDY (original) (raw)
Related papers
Single Image Super Resolution Algorithms: A Survey and Evaluation
— Image processing sub branch that specifically deals with the improvement, of images and videos, resolution without compromising the detail and visual effect but rather enhances the two, is known as Super Resolution. Multiple (multiple input images and one output image) or single (one input and one output) low resolution images are converted to high resolution. Single image super resolution algorithms are more practical since multiple images are not always available. The paper presents a survey of recent single image super resolution methods that are based on the use of external database to predict the values of missing pixels in high resolution image.
Literature Review on Single Image Super Resolution
International Journal of Trend in Scientific Research and Development
In this paper, a detailed survey study on single image super-resolution (SR) has been presented, which aims at recovering a high-resolution (HR) image from a given low-resolution (LR) one. It is always the research emphasis because of the requirement of higher definition video displaying, such as the new generation of Ultra High Definition (UHD) TVs. Super-resolution (SR) is a popular topic of image processing that focuses on the enhancement of image resolution. In general, SR takes one or several low resolution (LR) images as input and maps output images with high resolution (HR), which has been widely applied in remote sensing, medical imaging, biometric identification.
A STUDY ON IMAGE SUPER-RESOLUTION TECHNIQUES
Image Super-Resolution (SR) is a technique to reconstruct High-Resolution (HR) images using one or more Low-Resolution (LR) images. This paper brings about a detailed study on image Super-Resolution Techniques. Different categories of image Resolution and the process, Image Super-Resolution are well described. A detailed description of different SR approaches is given and certain relevant SR methods are explained. This paper also gives a qualitative and quantitative performance evaluation and comparison of various SR methods.
IJERT-Single Image Super-Resolution - A Quantitative Comparison
International Journal of Engineering Research and Technology (IJERT), 2015
https://www.ijert.org/single-image-super-resolution-a-quantitative-comparison https://www.ijert.org/research/single-image-super-resolution-a-quantitative-comparison-IJERTV4IS050888.pdf Super-resolution (SR) techniques generates high resolution (HR) image from low resolution (LR) images. Since HR image contains more information than LR image, it is severely demanding for all applications of image analysis. High resolution images improves the pictorial information for both human and automatic machine perception. This paper presents a comparison on well-known techniques of super resolution. Performance of the algorithms are evaluated by means of objective image quality criteria like Peak Signal to Ratio (PSNR), Structural Similarity Index (SSIM) and Maximum Difference (MD). From the analysis we have found that learning based algorithm using sparse dictionary performs better.
A Comprehensive Review and Comparison of Image Super-resolution Techniques
International journal of advanced engineering, management and science, 2024
Image super-resolution (SR) is a pivotal task in computer vision and image processing, aiming to enhance the resolution and quality of low-resolution images. This review article provides an in-depth analysis and comparison of various image super-resolution techniques, including traditional methods and deep learning-based approaches. We discuss the underlying principles, algorithms, advantages, and limitations of each technique, along with their applications across diverse domains. Additionally, we highlight recent advancements, challenges, and future research directions in the field of image superresolution.
ANALYSIS OF SINGLE FRAME SUPER RESOLUTION METHODS
INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH (IJEDR) (ISSN:2321-9939), 2014
The Image Quality can be most often measured in terms of Resolution. The clarity of the Image can be determined by Resolution which means higher the resolution, the image can be more clearer which is most often required in most of the applications. It can be achieved by use of Good Sensors ad optics, but it can be very expensive and also limit way of pixel density within Image. Instead of that we can use image processing methods to obtain High resolution image from low resolution image which can very effective and cheap solution. This Kind of Image Enhancement is called Super Resolution Image Reconstruction. This paper focuses on the definition, implementation and analysis on well-known techniques of super resolution. The comparison and analysis are the main concerns to understand the improvements of the super resolution methods over single frame interpolation techniques. In addition, the comparison also gives us an insight to the practical uses of super resolution methods. As a result of the analysis, the critical examination of the techniques and their performance evaluation are achieved. Super Resolution is particularly useful in forensic imaging, where the extraction of minute details in an image can help to solve a major crime cases. Super-resolution image restoration has been one of the most important research areas in recent years which goals to obtain a high resolution (HR) image from low resolutions (LR) blurred, noisy, under sampled and displaced image.
Single-image reconstruction using novel super-resolution technique for large-scaled images
Soft Computing
A fast and novel method for single-image reconstruction using the super-resolution (SR) technique has been proposed in this paper. The working principle of the proposed scheme has been divided into three components. A low-resolution image is divided into several homogeneous or non-homogeneous regions in the first component. This partition is based on the analysis of texture patterns within that region. Only the non-homogeneous regions undergo the sparse representation for SR image reconstruction in the second component. The obtained reconstructed region from the second component undergoes a statistical-based prediction model to generate its more enhanced version in the third component. The remaining homogeneous regions are bicubic interpolated and reflect the required high-resolution image. The proposed technique is applied to some Large-scale electrical, machine and civil architectural design images. The purpose of using these images is that these images are huge in size, and processing such large images for any application is time-consuming. The proposed SR technique results in a better reconstructed SR image from its lower version with low time complexity. The performance of the proposed system on the electrical, machine and civil architectural design images is compared with the state-of-the-art methods, and it is shown that the proposed scheme outperforms the other competing methods.
A Review on Super Resolution Techniques
In review paper [4], authors Huahua Chen, Baolin Jiang, Weiqiang Chen have demonstrated that a super-resolution based on image patches structure. This method have not only has better quality but less consuming time than Yang [11] method.
International Journal of Engineering Research and Technology (IJERT), 2012
https://www.ijert.org/single-image-super-resolution https://www.ijert.org/research/single-image-super-resolution-IJERTV1IS10412.pdf These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. This computationally inexpensive method is robust to errors in motion and blur estimation and results in images with sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods. The SR image approaches reconstruct a single higher-resolution image from a set of given lower-resolution images For the reconstruction stage a SR reconstruction model composed of the L1 normdata fidelity and total variation (TV) regularization is defined, with its reconstruction object function being efficiently solved by the steepest descent method. Other SR methods can be easily incorporated in the proposed framework as well. Specifically, the SR computations for multi-view images computation in the temporal domain are discussed.
Single Image Super-Resolution and Complexity-Quality Trade Off
International Journal of Engineering Applied Sciences and Technology
Single Image Super-Resolution is a challenging task that aims to enhance the quality of the image from low resolution to high resolution. Superresolution techniques can also be used as image lossy compression-decompression technique where low-res image is transmitted and decoded into high-res version at the received end. Various methods have been introduced till date, including algorithmic interpolation methods and deep learning methods. The algorithmic methods such as bilinear interpolation, bicubic interpolation, nearest neighbor and others provide fast processing while deep learning methods provide better quality of superresolution image. We analyzed the time required to process images using various methods and compared them with the perceptual quality along with the variation in perceptual quality and PSNR metrics.