Super Resolution Using Neural Network

Patil, Varsha; Bormane, D. S.; Pawar, Vaishali

doi:10.1109/ams.2008.140

Cited by 11 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually it is used to decompose the input image into structurally correlated sub-images. This allows exploiting the self-similarities between local neighboring regions [356], [516]. For example, in [516] the input image is first decomposed into subbands.…”

Section: Wavelet Transformmentioning

confidence: 99%

Super-resolution: a comprehensive survey

Nasrollahi

Moeslund

2014

Machine Vision and Applications

592

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: Wavelet Transformmentioning

confidence: 99%

Super-resolution: a comprehensive survey

Nasrollahi

Moeslund

2014

Machine Vision and Applications

592

292

View full text Add to dashboard Cite

show abstract

“…Where M and N are the maximum values of the dimensions of low resolution images m,n, respectively. Combining eq (5)into eq(7) and writing the results in matrix forms, gives us…”

Section: Fourier Transformmentioning

confidence: 99%

“…Wavelet Transform is used to decompose the input image into structurally correlated subimages. This gives us the self-similarities between local neighboring regions [5], [6]. For example, in [6] the input image is first decomposed into subbands.…”

Section: Wavelet Transformmentioning

confidence: 99%

Single and Multi frame Image super-resolution and its Performance Analysis: A Comprehensive Survey

Chopade¹,

Patil²

2015

IJCA

View full text Add to dashboard Cite

Super-resolution is the process of combining one or more low-resolution images to obtain a high-resolution image. It has been a very interesting topic for the research over the last few years. It is used for practical applications in more realistic problems faced in different areas, which range over satellite and aerial imaging of biomedical image processing as well as in daily routine life like different biometrics in offices and industries. In this survey article, more focus is given on basic algorithms and their classification based methodology used to implement it. Due to its vast scope of applications researchers are developing a novel suerresolution algorithm for a specific intention based on single and multiframe image resolution. The proposed comprehensive survey gives an overview of most of published works based on its performance analysis. In this survey, the basic concepts of the algorithms are explained and then their performance analyses through which each of these methods have developed are mentioned in detail. Furthermore, different issues in superresolution algorithms for single and multiframesuch as models and registration algorithms, optimization of the deployment of methods, improvement in quality of image .

show abstract

“…End-to-end models are composed of various networks [22] in which parameters can be automatically updated by forward and afterward propagation. These models [18][19][20][21][22][23][24][25][26][27] are designed for natural images, which provide references for the SR task of remote sensing images. Patil et al [23] proposed using a neural network to extract the structural correlation and predict fine details of reconstructed images.…”

Section: Introductionmentioning

confidence: 99%

A Super-Resolution Algorithm Based on Hybrid Network for Multi-Channel Remote Sensing Images

Zhang

Pan

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

In recent years, the development of super-resolution (SR) algorithms based on convolutional neural networks has become an important topic in enhancing the resolution of multi-channel remote sensing images. However, most of the existing SR models suffer from the insufficient utilization of spectral information, limiting their SR performance. Here, we derive a novel hybrid SR network (HSRN) which facilitates the acquisition of joint spatial–spectral information to enhance the spatial resolution of multi-channel remote sensing images. The main contributions of this paper are three-fold: (1) in order to sufficiently extract the spatial–spectral information of multi-channel remote sensing images, we designed a hybrid three-dimensional (3D) and two-dimensional (2D) convolution module which can distill the nonlinear spectral and spatial information simultaneously; (2) to enhance the discriminative learning ability, we designed the attention structure, including channel attention, before the upsampling block and spatial attention after the upsampling block, to weigh and rescale the spectral and spatial features; and (3) to acquire fine quality and clear texture for reconstructed SR images, we introduced a multi-scale structural similarity index into our loss function to constrain the HSRN model. The qualitative and quantitative comparisons were carried out in comparison with other SR methods on public remote sensing datasets. It is demonstrated that our HSRN outperforms state-of-the-art methods on multi-channel remote sensing images.

show abstract

Super Resolution Using Neural Network

Cited by 11 publications

References 7 publications

Super-resolution: a comprehensive survey

Super-resolution: a comprehensive survey

Single and Multi frame Image super-resolution and its Performance Analysis: A Comprehensive Survey

A Super-Resolution Algorithm Based on Hybrid Network for Multi-Channel Remote Sensing Images

Contact Info

Product

Resources

About