基于多通道极深卷积神经网络的图像超分辨率算法  

Super-Resolution Algorithm for Images Based on Multi-ChannelExtremely Deep Convolutional Neural Network

作　　者：黄伟 冯晶晶 黄遥 HUANG Wei;FENG Jingjing;HUANG Yao(School of Computer and Communication Engineering,Zhengzhou University of Light Industry,Zhengzhou 450002,China)

机构地区：[1]郑州轻工业大学计算机与通信工程学院,郑州450002

出　　处：《计算机工程》2020年第9期242-247,253,共7页Computer Engineering

基　　金：国家自然科学基金(61602423);河南省科技公关项目(172102410088)。

摘　　要：卷积神经网络(CNN)在单幅图像超分辨率重构中存在网络结构较浅、可提取特征较少和细节重构效果不显著等问题。为此,提出一种基于多通道极深CNN的图像超分辨率算法,分别对原始低分辨率图像进行3种插值和3种锐化等预处理操作,并以多通道图像作为CNN的输入层数据。通过重新调整卷积核大小以加深网络结构,使得输入层数据在极深的CNN模型中训练重构高分辨率图像。实验结果表明,与Bicubic、SRCNN和MC-SRCNN等算法相比,该算法的峰值信噪比和视觉效果均较好。When applied in the super-resolution reconstruction of a single image,the structure of Convolutional Neural Network(CNN)is shallow,and the number of features that can be extracted is reduced,which weakens the reconstruction performance of details.To address the problem,this paper proposes a super-resolution reconstruction algorithm for images based on extremely deep CNN using multi-channel input.Three interpolation and three sharpening preprocessing operations are performed on the original low-resolution image respectively,and the multi-channel image is used as data of the input layer of CNN.At the same time,the size of the convolution kernel is readjusted to deepen the network structure,so that the data of the input layer is trained in an extremely deep CNN model to reconstruct high-resolution images.Experimental results show that compared with Bicubic,SRCNN,MC-SRCNN and other algorithms,this algorithm has a better Peak Signal-to-Noise Ratio(PSNR)and visual effects.

关 键 词：卷积神经网络 超分辨率重构 多通道图像 卷积核 极深网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]