Learning spatially-variable filters for super-resolution of text

Corduneanu, Adrian; Platt, John

doi:10.1109/icip.2005.1529884

Cited by 8 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in - [13], [138], [151], [180], [246], [286], [322], [367], [386], [391], [537], [538], [545] the images are first converted to YIQ color space (in [162], [557], [558], [608] to YCbCr). Since most of the energy in these representations is concentrated in the luminance component, Y, the SR algorithm is first applied to this Color Space Reported in YIQ [13], [151], [180], [246], [286], [322], [367], [386], [391], [537], [538], [545] YCbCr [160], [162], [557], [558], [608] RGB [117], [155], [156], [157], [158], [226], [227], [377] YUV [203], [216], [287], [392], …”

Section: Color Imagesmentioning

confidence: 99%

Super-resolution: a comprehensive survey

Nasrollahi

Moeslund

2014

Machine Vision and Applications

589

292

View full text Add to dashboard Cite

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 superresolution 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.

show abstract

Section: Color Imagesmentioning

confidence: 99%

Super-resolution: a comprehensive survey

Nasrollahi

Moeslund

2014

Machine Vision and Applications

589

292

View full text Add to dashboard Cite

show abstract

“…One work similar in spirit to ours is [3]. There the authors also try to express the center pixel as a linear combination of its neighbors.…”

Section: Introductionmentioning

confidence: 99%

Variational Local Structure Estimation for Image Super-Resolution

Lian

2006

2006 International Conference on Image Processing

View full text Add to dashboard Cite

Super-resolution is an important but difficult problem in image/video processing. If a video sequence or some training set other than the given low-resolution image is available, this kind of extra information can greatly aid in the reconstruction of the high-resolution image. The problem is substantially more difficult with only a single low-resolution image on hand. The image reconstruction methods designed primarily for denoising is insufficient for super-resolution problem in the sense that it tends to oversmooth images with essentially no noise. We propose a new adaptive linear interpolation method based on variational method and inspired by local linear embedding (LLE). The experimental result shows that our method avoids the problem of oversmoothing and preserves image structures well.

show abstract

“…Based on the idea in [91], Dalley et al [92] proposed a single-frame text SR method by adopting a full-Bayesian approach with an explicit noise model. In [93], a novel algorithm for text SR was developed by interpolation with a variable linear filter. The filter is modeled as a linear function of edge patterns, whose parameters can be trained in a text database.…”

Section: Learning-based Domain-specific Image Super-resolution Methodsmentioning

confidence: 99%

High-resolution image reconstruction using super-resolution and deconvolution techniques

He¹

View full text Add to dashboard Cite

This thesis investigates the techniques for high-resolution (HR) image reconstruction through image super-resolution (SR) and deconvolution algorithms. In many imaging applications, HR images are desired, but may not be available due to practical limitations. Using HR reconstruction, it is possible to restore high-frequency content, reduce noise, and increase spatial resolution when hardware modification is unrealizable. In the first part of this thesis, we address the multi-frame SR from two points of view: blur identification and motion estimation. Multi-frame SR is the fusion of a set of LR images to produce a HR image. A main issue arising from the multi-frame SR problem is the availability of the knowledge on the blurring occurred during the image formation process. In many real-world applications, it is often difficult to know the blurring completely a priori. In view of this, we present a new soft maximum a posteriori (MAP) estimation framework to perform joint blur identification and HR image reconstruction. The proposed method incorporates a soft blur prior that estimates the relevance of the best-fit parametric blur model, and induces reinforcement learning towards it. An iterative scheme based on alternating minimization is developed to estimate the blur and HR image progressively. Another critical step in multi-frame SR is accurate motion estimation of the LR images, particularly when the motion is not purely translational between the LR images. In view of this, we present a new framework that performs simultaneous image registration and HR image reconstruction in Chapter 4. This is promising as more accurate motion parameters can be determined, thereby enhancing the performance of the HR reconstruction. Further, it is worth noting that unlike most algorithms that focus on the translational motion model, the proposed method adopts a more generic motion model that includes both translation as well as rotation. An iterative scheme is developed to solve the

show abstract

Learning spatially-variable filters for super-resolution of text

Cited by 8 publications

References 8 publications

Super-resolution: a comprehensive survey

Super-resolution: a comprehensive survey

Variational Local Structure Estimation for Image Super-Resolution

High-resolution image reconstruction using super-resolution and deconvolution techniques

Contact Info

Product

Resources

About