scholarly journals Perceptual Image Super Resolution Using Deep Learning and Super Resolution Convolution Neural Networks (SRCNN)

2020 ◽  
Author(s):  
Nagaraj P ◽  
Muthamilsudar K ◽  
Naga Nehanth S ◽  
Mohammed Shahid R ◽  
Sujith Kumar V
Keyword(s):  
Neural Network ◽  
Mean Squared Error ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Convolution Neural Network ◽  
Resolution Image ◽  
Squared Error ◽  
Image Super Resolution ◽  
The Mean ◽  
State Of Art

The main objective of Perceptual Image Super Resolution is to obtain a high resoluted image from a normal low resolution image. The task is very simple that we just want to make a Low firmness appearance into a extraordinary resolution image. To perform this task we have various methods like Classical Approach in which we try to maximize the mean squared error, evaluate by PSNR(Peak-Signal-to-Noise-Ratio). The first method used to perform this operation was SRCNN (Super Resolution Convolution Neural Network) and these days many of them use DRCN and VDSR which are slightly upgraded methods. Another technique used for the purpose of upscaling to get a high resoluted image from normal little resolution image is the state of art by PSNR. This method was a quite simple one in which we take a low determination image as input and place in a convolution neural network(CNN) and produce a high resolution image as the output. In this technique the edges will be clearly defined, but the whole image will be blurred. This method is unable to produce good-looking textures.

Gaussian Noised Single-Image Super Resolution Reconstruction

2013 ◽  
Vol 457-458 ◽  
pp. 1032-1036
Author(s):  
Feng Qing Qin ◽  
Li Hong Zhu ◽  
Li Lan Cao ◽  
Wa Nan Yang
Keyword(s):  
Gaussian Noise ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Projection Algorithm ◽  
Single Image ◽  
Low Resolution ◽  
Filtering Algorithm ◽  
Resolution Image ◽  
Image Super Resolution ◽  
Single Image Super Resolution

A framework is proposed to reconstruct a super resolution image from a single low resolution image with Gaussian noise. The degrading processes of Gaussian blur, down-sampling, and Gaussian noise are all considered. For the low resolution image, the Gaussian noise is reduced through Wiener filtering algorithm. For the de-noised low resolution image, iterative back projection algorithm is used to reconstruct a super resolution image. Experiments show that de-noising plays an important part in single-image super resolution reconstruction. In the super reconstructed image, the Gaussian noise is reduced effectively and the peak signal to noise ratio (PSNR) is increased.

scholarly journals Penerapan Jaringan Saraf Tiruan Dalam Memprediksi Indikator Utama Ekonomi Dunia

2018 ◽  
Vol 2 (2) ◽  
pp. 169
Author(s):  
Alan Boy Sandy Damanik ◽  
Agung Bimantoro
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Mean Squared Error ◽  
Economic Indicator ◽  
Squared Error ◽  
The World ◽  
Artificial Neural Network Method ◽  
World Economic ◽  
Architectural Models ◽  
The Mean

Economics is one of the most important aspects in the world. Economics greatly determines the progress and development of a country. However, there are still many countries with low economic levels. Therefore the aim of this study is to predict and determine the level of the main indicators of the world economy as one of the anticipatory steps to further increase the level of the country's economy. World Economic Indicator Data to be used is sourced from Bloomberg and Bank Indonesia. To find out further developments, it is necessary to research the existing data. The algorithm used is Backpropagatian Neural Network. Data analysis was carried out using artificial neural network method using Matlab R2011b software. The study uses 5 architectural models. The best network architecture produced is 3-43-1 with an accuracy rate of 86% and the Mean Squared Error (MSE) value is 1.336593.

An MMSE Overlay Cognitive Wireless System

2013 ◽  
Vol 5 (1) ◽  
pp. 1-13
Author(s):  
Monirosharieh Vameghestahbanati ◽  
Hasan S. Mir ◽  
Mohamed El-Tarhuni
Keyword(s):  
Mean Squared Error ◽  
Signal To Noise Ratio ◽  
Signal To Noise ◽  
Wireless System ◽  
Transmitter Power ◽  
Channel Estimate ◽  
Squared Error ◽  
The Mean ◽  
Noise Ratio ◽  
New System

In this paper, the authors propose a framework that allows an overlay (new) system to operate simultaneously with a legacy (existing) system. By jointly optimizing the transmitter and the receiver filters of the overlay system, the sum of the mean-squared error (MSE) of the new system plus the excess MSE in the existing system due to the introduction of the overlay system is minimized. The effects of varying key parameters such as the overlay transmitter power and the amount of overlap between the legacy and the overlay systems are investigated. Furthermore, the sensitivity of the system to accuracy of signal-to-noise ratio (SNR) estimate and the channel estimate is also examined.

scholarly journals New Access to Improve Super Resolution using Convolution Neural Network

2019 ◽  
Vol 8 (6S) ◽  
pp. 160-165
Keyword(s):  
Neural Network ◽  
Image Quality ◽  
Super Resolution ◽  
Convolution Neural Network ◽  
Low Resolution ◽  
Filtration Method ◽  
Resolution Image ◽  
Smoothness Index ◽  
Preprocessing Technique ◽  
Filtration Technique

Super Resolution is the process to enhance image quality by increasing the pixel densities from a low resolution image. Several methods are proposed in the last few decades. We survey several methods like filtration method i.e. Scalar Smoothness Index filtration, learning based method using Convolution Neural Network. We also propose a new algorithm where we use filtration technique as a preprocessing technique of learning based method.

Sign in / Sign up

Export Citation Format

Share Document