测试科学与仪器2022，Vol.13Issue(3)：276-283,8.DOI:10.3969/j.issn.1674-8042.2022.03.004
基于极深超分辨率卷积神经网络的单一图像超分辨率研究
Research on single image super-resolution based on very deep super-resolution convolutional neural network
黄璋豫1
作者信息
- 1. 伯明翰大学电子电气与系统工程系,英国B152TT
- 折叠
摘要
Abstract
Single image super-resolution(SISR)is a fundamentally challenging problem because a low-resolution(LR)image can correspond to a set of high-resolution(HR)images,while most are not expected.Recently,SISR can be achieved by a deep learning-based method.By constructing a very deep super-resolution convolutional neural network(VDSRCNN),the LR images can be improved to HR images.This study mainly achieves two objectives:image super-resolution(ISR)and deblurring the image from VDSRCNN.Firstly,by analyzing ISR,we modify different training parameters to test the performance of VDSRCNN.Secondly,we add the motion blurred images to the training set to optimize the performance of VDSRCNN.Finally,we use image quality indexes to evaluate the difference between the images from classical methods and VDSRCNN.The results indicate that the VDSRCNN performs better in generating HR images from LR images using the optimized VDSRCNN in a proper method.关键词
单图像超分辨率/极深超分辨卷积神经网络/运动模糊图像/图像质量指数Key words
single image super-resolution(SISR)/very deep super-resolution convolutional neural network(VDSRCNN)/motion blurred image/image quality index引用本文复制引用
黄璋豫..基于极深超分辨率卷积神经网络的单一图像超分辨率研究[J].测试科学与仪器,2022,13(3):276-283,8.
