Fast single image super-resolution by self-trained filtering
11 Aug 2011-pp 469-475
TL;DR: An algorithm to super-resolve an image based on a self-training filter (STF) that is more effective than a generic unsharp mask filter when compared to support vector regression methods and the kernel regression method.
Abstract: This paper introduces an algorithm to super-resolve an image based on a self-training filter (STF). As in other methods, we first increase the resolution by interpolation. The interpolated image has higher resolution, but is blurry because of the interpolation. Then, unlike other methods, we simply filter this interpolated image to recover some missing high frequency details by STF. The input image is first downsized at the same ratio used in super-resolution, then upsized. The super-resolution filters are obtained by minimizing the mean square error between the upsized image and the input image at different levels of the image pyramid. The best STF is chosen as the one with minimal error in the training phase. We have shown that STF is more effective than a generic unsharp mask filter. By combining interpolation and filtering, we achieved competitive results when compared to support vector regression methods and the kernel regression method.
Citations
More filters
01 Aug 2014
TL;DR: The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy, and common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super- resolution algorithms, and the most commonly employed databases are discussed.
Abstract: Super-resolution, the process of obtaining one or more high-resolution images from one or more low-resolution observations, has been a very attractive research topic over the last two decades. It has found practical applications in many real-world problems in different fields, from satellite and aerial imaging to medical image processing, to facial image analysis, text image analysis, sign and number plates reading, and biometrics recognition, to name a few. This has resulted in many research papers, each developing a new super-resolution algorithm for a specific purpose. The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy. For each of the groups in the taxonomy, the basic concepts of the algorithms are first explained and then the paths through which each of these groups have evolved are given in detail, by mentioning the contributions of different authors to the basic concepts of each group. Furthermore, common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super-resolution algorithms, and the most commonly employed databases are discussed.
602 citations
Additional excerpts
...401], Terrascope [299], Asian Face Database PF01 [328], FG-NET Database [342], Korean Face Database [356], Max Planck Institute Face Database [356], IMM Face Database [383], PAL [397,456], USC-SIPI [490,504,578], Georgia Tech [408,524], ViDTIMIT [401], FRI CVL [481], Face96 [481], FEI face database [572], MBGC face and iris database [586], SOFTPIA Japan Face Database [606]....
[...]
Patent•
29 Jul 2011TL;DR: In this article, the authors propose a method for image upscaling that includes anti-aliasing an input image and downsampling the input image to create a lower resolution image.
Abstract: An embodiment provides a method for image upscaling. The method includes anti-aliasing an input image and downsampling the input image to create a lower resolution image. The method also includes interpolating the lower resolution image to obtain a higher resolution image and creating a filter map from the input image and the higher resolution image. The method also includes upsampling the input image using the filter map to create a high-resolution image.
31 citations
TL;DR: A set of filters and parameters recommendations is offered based on extensive testing on carefully selected image datasets, focusing mostly on linear interpolation methods with symmetric kernels.
Abstract: In this paper, a set of techniques used for downsampling and upsampling of 2D images is analyzed on various image datasets. The comparison takes into account a significant number of interpolation kernels, their parameters, and their algebraical form, focusing mostly on linear interpolation methods with symmetric kernels. The most suitable metrics for measuring the performance of upsampling and downsampling filters’ combinations are presented, discussing their strengths and weaknesses. A test benchmark is proposed, and the obtained results are analyzed with respect to the presented metrics, offering explanations about specific filter behaviors in general, or just in certain circumstances. In the end, a set of filters and parameters recommendations is offered based on extensive testing on carefully selected image datasets. The entire research is based on the study of a large set of research papers and on a solid discussion of the underlying signal processing theory.
18 citations
Cites background from "Fast single image super-resolution ..."
...Modern approaches using PDEs, statistical processing, wavelet analysis, image inpainting, and artificial intelligence are of high interest [21,22,39]....
[...]
13 Nov 2013
TL;DR: In this article, a technique for satellite imagery spatial resolution enhancement based on subpixel multiple image registration is presented. But this technique is not suitable for remote sensing applications, as the spatial resolution of the images is limited and the uncertainty in satellite imagery classification and analysis leads to uncertainty in the analysis.
Abstract: Development of new satellite imagery processing algorithms for resolution enhancement and subpixel analysis allows to increase efficiency of remote sensing applications. Insufficiency of the spatial resolution leads to uncertainty in satellite imagery classification and analysis. In this paper we present the technique for satellite imagery spatial resolution enhancement based on subpixel multiple image registration.
4 citations
Cites background from "Fast single image super-resolution ..."
...It can be nonuniform interpolation [6], frequency domain regularization [7], maximum a posteriori reconstruction [8], constrained least squares estimation [9], projection onto convex sets [10], iterative back-projection [11], adaptive matched filtering [12], etc....
[...]
29 May 2013
TL;DR: This paper presents the technique for satellite imagery spatial resolution enhancement based on subpixel multiple image registration, which allows to increase efficiency of remote sensing applications.
Abstract: Development of new satellite imagery processing algorithms for resolution enhancement and subpixel analysis allows to increase efficiency of remote sensing applications. Insufficiency of the spatial resolution leads to uncertainty in satellite imagery classification and analysis. In this paper we present the technique for satellite imagery spatial resolution enhancement based on subpixel multiple image registration.
3 citations
Cites background from "Fast single image super-resolution ..."
...It can be nonuniform interpolation [6], frequency domain regularization [7], maximum a posteriori (MAP) reconstruction [8], constrained least squares estimation [9], projection onto convex sets [10], iterative back-projection [11], adaptive matched filtering [12], etc....
[...]
References
More filters
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Abstract: LIBSVM is a library for Support Vector Machines (SVMs). We have been actively developing this package since the year 2000. The goal is to help users to easily apply SVM to their applications. LIBSVM has gained wide popularity in machine learning and many other areas. In this article, we present all implementation details of LIBSVM. Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
40,826 citations
Book•
01 Jan 1995TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Abstract: Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.
40,147 citations
"Fast single image super-resolution ..." refers methods in this paper
...Our previous work has introduced support vector regression [5] in a number of image processing tasks including blind image deconvolution [6], image denoising [7] and superresolution [8] and [9]....
[...]
TL;DR: This work built on another training-based super- resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution that requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data.
Abstract: We call methods for achieving high-resolution enlargements of pixel-based images super-resolution algorithms. Many applications in graphics or image processing could benefit from such resolution independence, including image-based rendering (IBR), texture mapping, enlarging consumer photographs, and converting NTSC video content to high-definition television. We built on another training-based super-resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution. Our algorithm requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data. This one-pass super-resolution algorithm is a step toward achieving resolution independence in image-based representations. We don't expect perfect resolution independence-even the polygon representation doesn't have that-but increasing the resolution independence of pixel-based representations is an important task for IBR.
2,576 citations
"Fast single image super-resolution ..." refers methods in this paper
...In the example-based super-resolution method [4], an image is...
[...]
TL;DR: This paper adapt and expand kernel regression ideas for use in image denoising, upscaling, interpolation, fusion, and more and establishes key relationships with some popular existing methods and shows how several of these algorithms are special cases of the proposed framework.
Abstract: In this paper, we make contact with the field of nonparametric statistics and present a development and generalization of tools and results for use in image processing and reconstruction. In particular, we adapt and expand kernel regression ideas for use in image denoising, upscaling, interpolation, fusion, and more. Furthermore, we establish key relationships with some popular existing methods and show how several of these algorithms, including the recently popularized bilateral filter, are special cases of the proposed framework. The resulting algorithms and analyses are amply illustrated with practical examples
1,457 citations
"Fast single image super-resolution ..." refers methods in this paper
...Kernel Regression (KR) [3] was recently introduced as a tool for image denoising, upscaling, interpolation, fusion etc....
[...]
...Table 2 lists the results when Kernel Regression (KR) [3] is used as the interpolation method....
[...]
TL;DR: In this article, an efficient algorithm for the continuous representation of a discrete signal in terms of B-splines and for interpolative signal reconstruction with an expansion factor m are described.
Abstract: Efficient algorithms for the continuous representation of a discrete signal in terms of B-splines (direct B-spline transform) and for interpolative signal reconstruction (indirect B-spline transform) with an expansion factor m are described. Expressions for the z-transforms of the sampled B-spline functions are determined and a convolution property of these kernels is established. It is shown that both the direct and indirect spline transforms involve linear operators that are space invariant and are implemented efficiently by linear filtering. Fast computational algorithms based on the recursive implementations of these filters are proposed. A B-spline interpolator can also be characterized in terms of its transfer function and its global impulse response (cardinal spline of order n). The case of the cubic spline is treated in greater detail. The present approach is compared with previous methods that are reexamined from a critical point of view. It is concluded that B-spline interpolation correctly applied does not result in a loss of image resolution and that this type of interpolation can be performed in a very efficient manner. >
510 citations