Resolution enhancement of textual images: a survey of single image‐based methods

Walha, Rim; Drira, Fadoua; Lebourgeois, Frank; Alimi, Adel M.; García, Christophe

doi:10.1049/iet-ipr.2015.0334

Cited by 20 publications

(7 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, text images are images which mainly have very low and very high frequencies alone unlike most natural images. As pointed out in [55],…”

Section: Domain-specific Interpolationmentioning

confidence: 87%

“…On the other hand, text images are images which mainly have very low and very high frequencies alone unlike most natural images. As pointed out in [55], text images have sudden discontinuity, regularity in fine pattern and continuity of same intensity values along a particular direction. As our proposed approach is not targeted to work specifically on such special images, we do not expect it to perform well in text images.…”

Section: Domain-specific Interpolationmentioning

confidence: 94%

See 1 more Smart Citation

Across-scale process similarity based interpolation for image super-resolution

Dhara

Sen

2019

Applied Soft Computing

View full text Add to dashboard Cite

A pivotal step in image super-resolution techniques is interpolation, which aims at generating high resolution images without introducing artifacts such as blurring and ringing. In this paper, we propose a technique that performs interpolation through an infusion of high frequency signal components computed by exploiting 'process similarity'. By 'process similarity', we refer to the resemblance between a decomposition of the image at a resolution to the decomposition of the image at another resolution. In our approach, the decompositions generating image details and approximations are obtained through the discrete wavelet (DWT) and stationary wavelet (SWT) transforms. The complementary nature of DWT and SWT is leveraged to get the structural relation between the input image and its low resolution approximation. The structural relation is represented by optimal model parameters obtained through particle swarm optimization (PSO). Owing to process similarity, these parameters are used to generate the high resolution output image from the input image. The proposed approach is compared with six existing techniques qualitatively and in terms of PSNR, SSIM, and FSIM measures, along with computation time (CPU time).It is found that our approach is the fastest in terms of CPU time and produces comparable results. Recently, few end to end deep neural networks have been proposed for superresolution. SRCNN [30, 31] uses the convolutional neural network (CNN) [32] for image super-resolution. The technique is later extended to DRCN [9] by increasing the number of layers of the network and incorporating recursive learning.The techniques proposed in [8,11] use residual learning in deep and very deep If the aforesaid wavelet based analysis and synthesis is considered for interpolation, then, the input low resolution image can be decomposed into its immediate lower resolution approximation (LL) using (2) and high frequency details using (3). Now, one can assume that only the lower approximation is available for synthesizing back the input image, and not the high frequency details. In such a case, one can try to estimate the unavailable high frequency

show abstract

“…On the other hand, text images are images which mainly have very low and very high frequencies alone unlike most natural images. As pointed out in [55],…”

Section: Domain-specific Interpolationmentioning

confidence: 87%

Section: Domain-specific Interpolationmentioning

confidence: 94%

Across-scale process similarity based interpolation for image super-resolution

Dhara

Sen

2019

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…A complete survey of these approaches is beyond the scope of this work. Readers can refer to a recent survey (Walha et al 2016;Agustsson and Timofte 2017) on super-resolution approaches for details. Here, we focus on discussing recent video super-resolution approaches based on deep network.…”

Section: Related Workmentioning

confidence: 99%

Frame and Feature-Context Video Super-Resolution

Yan

Lin

2019

AAAI

View full text Add to dashboard Cite

For video super-resolution, current state-of-the-art approaches either process multiple low-resolution (LR) frames to produce each output high-resolution (HR) frame separately in a sliding window fashion or recurrently exploit the previously estimated HR frames to super-resolve the following frame. The main weaknesses of these approaches are: 1) separately generating each output frame may obtain high-quality HR estimates while resulting in unsatisfactory flickering artifacts, and 2) combining previously generated HR frames can produce temporally consistent results in the case of short information flow, but it will cause significant jitter and jagged artifacts because the previous super-resolving errors are constantly accumulated to the subsequent frames. In this paper, we propose a fully end-to-end trainable frame and feature-context video super-resolution (FFCVSR) network that consists of two key sub-networks: local network and context network, where the first one explicitly utilizes a sequence of consecutive LR frames to generate local feature and local SR frame, and the other combines the outputs of local network and the previously estimated HR frames and features to super-resolve the subsequent frame. Our approach takes full advantage of the inter-frame information from multiple LR frames and the context information from previously predicted HR frames, producing temporally consistent highquality results while maintaining real-time speed by directly reusing previous features and frames. Extensive evaluations and comparisons demonstrate that our approach produces state-of-the-art results on a standard benchmark dataset, with advantages in terms of accuracy, efficiency, and visual quality over the existing approaches.

show abstract

“…By using the proposed dynamic sampling concept in combination with the proposed reconstruction algorithm, a video sequence with both a high spatial and a high temporal resolution can be acquired. Additionally, other methods from frame rate up-conversion (FRUC) [5], [6] and super-resolution (SR) [7], [8], [9], [10], [11], [12] which are also able to reconstruct such sequences are used for comparison.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Non-Regular Sampling Sensor Using Frequency Selective Reconstruction

Jonscher,

Seiler,

Lanz

et al. 2022

Preprint

View full text Add to dashboard Cite

Resolution enhancement of textual images: a survey of single image‐based methods

Cited by 20 publications

References 62 publications

Across-scale process similarity based interpolation for image super-resolution

Across-scale process similarity based interpolation for image super-resolution

Frame and Feature-Context Video Super-Resolution

Dynamic Non-Regular Sampling Sensor Using Frequency Selective Reconstruction

Contact Info

Product

Resources

About