Video Super Resolution by Neural Network: A Theoretical Aspect

2020 ◽  
Vol 17 (9) ◽  
pp. 4202-4206
Author(s):  
Mrunmayee V. Daithankar ◽  
Sachin D. Ruikar
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Super Resolution ◽  
Theoretical Aspect ◽  
Neural Network Architecture ◽  
Enhanced Resolution ◽  
Resolution Improvement ◽  
The Neural Networks ◽  
New Generation ◽  
Practical Feasibility

The paper explores literature on the video super resolution by neural network, with all essential basics related to it. The extensive applicability and need of enhanced resolution becomes attraction for researchers. The limitations of traditional methods gives rise to the new generation of neural network based super resolution. The neural networks are well known for parallel and fast computation of data. But embedding a neural network with challenging super resolution era has come up with benefits as well as drawbacks. Still the researchers are working on the challenges like, limited practical feasibility and utility, accuracy at the time cost, complexity, etc. This paper is useful for new researchers to get information about the basics of super resolution and neural network, relative study of learning processes, comparative summarization of neural network architecture used for resolution improvement.

Real-Time Video Scaling Based on Convolution Neural Network Architecture

2017 ◽  
Vol 7 (2) ◽  
pp. 381
Author(s):  
S Safinaz ◽  
AV Ravi kumar
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Real Time ◽  
Network Architecture ◽  
High Efficiency ◽  
Super Resolution ◽  
Reconstruction Error ◽  
Convolution Neural Network ◽  
Neural Network Architecture ◽  
Video Frames

In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network) shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

scholarly journals Large receptive field networks for accurate high-scale image super-resolution

2021 ◽  
Author(s):  
George Seif
Keyword(s):  
Neural Network ◽  
Receptive Field ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Super Resolution ◽  
Neural Network Architecture ◽  
High Scale ◽  
One Dimensional ◽  
Image Super Resolution ◽  
And Performance

This thesis presents a novel convolutional neural network architecture for high-scale image super-resolution. In particular, we introduce two separate modifications that can be made to the convolutional layers in the network: one-dimensional kernels and dilated kernels. We show how both of these methods can be used to expand the receptive field and performance of super-resolution networks, without increasing the number of trainable parameters or network depth. We show that these modifications can easily be integrated into any convolutional neural network to improve performance. Our methods are especially effective for the challenging high scale super-resolution due to the expanded network receptive field. We conduct extensive empirical evaluations to demonstrate the effectiveness of our methods, showing strong improvements over the state-of-the-art.

scholarly journals Large receptive field networks for accurate high-scale image super-resolution

2021 ◽  
Author(s):  
George Seif
Keyword(s):  
Neural Network ◽  
Receptive Field ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Super Resolution ◽  
Neural Network Architecture ◽  
High Scale ◽  
One Dimensional ◽  
Image Super Resolution ◽  
And Performance

This thesis presents a novel convolutional neural network architecture for high-scale image super-resolution. In particular, we introduce two separate modifications that can be made to the convolutional layers in the network: one-dimensional kernels and dilated kernels. We show how both of these methods can be used to expand the receptive field and performance of super-resolution networks, without increasing the number of trainable parameters or network depth. We show that these modifications can easily be integrated into any convolutional neural network to improve performance. Our methods are especially effective for the challenging high scale super-resolution due to the expanded network receptive field. We conduct extensive empirical evaluations to demonstrate the effectiveness of our methods, showing strong improvements over the state-of-the-art.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Sign in / Sign up

Export Citation Format

Share Document