摘要
针对传统图像超分辨率重建方法存在的重建图像模糊、噪声量大、视觉感差等问题,提出了一种基于混合深度卷积网络的图像超分辨率重建方法。首先,在上采样阶段将低分辨率图像放缩至指定大小;然后,在特征提取阶段提取低分辨率图像的初始特征;接着,将提取到的初始特征送入卷积编解码结构进行图像特征去噪;最后,在重建层用空洞卷积进行高维特征提取与运算,重建出高分辨率图像,并且使用残差学习快速优化网络,在降低噪声的同时,使重建图像的清晰度及视觉效果更优。在Set14数据集放大尺度×4的基准下,将所提方法与双三次插值(Bicubic)、锚定邻域回归(A+)、超分辨卷积神经网络(SRCNN)、极深度超分辨网络(VDSR)、编解码网络(REDNet)等超分辨率重建方法进行对比。在超分辨实验中,所提方法与对比方法比较,峰值信噪比(PSNR)分别提升了2.73 dB、1.41 dB、1.24 dB、0.72 dB和1.15 dB,结构相似性(SSIM)分别提高了0.0673,0.0209,0.0197,0.0026和0.0046。实验结果表明,混合深度卷积网络能够有效地对图像进行超分辨率重建。
Aiming at the problems of blurred image,large noise,and poor visual perception in the traditional image super-resolution reconstruction methods,a method of image super-resolution reconstruction based on hybrid deep convolutional network was proposed.Firstly,the low-resolution image was scaled down to the specified size in the upsampling phase.Secondly,the initial features of the low-resolution image were extracted in the feature extraction phase.Thirdly,the extracted initial features were sent to the convolutional coding and decoding structure for image feature denoising.Finally,high-dimensional feature extraction and computation were performed on the reconstruction layer using the dilated convolution in order to reconstruct the high-resolution image,and the residual learning was used to quickly optimize the network in order to reduce the noise and make the reconstructed image have better definition and visual effect.Based on the Set14 dataset and scale of 4 x,the proposed method was compared with Bicubic interpolation(Bicubic),Anchored neighborhood regression(A+),Super-Resolution Convolutional Neural Network(SRCNN),Very Deep SuperResolution network(VDSR),Restoration Encoder-Decoder Network(REDNet).In the super-resolution experiments,compared with the above methods,the proposed method has the Peak Signal-to-Noise Ratio(PSNR)increased by 2.73 dB,1.41 dB,1.24 dB,0.72 dB and 1.15 dB respectively,and the Structural SIMilarity(SSIM)improved by 0.0673,0.0209,0.0197,0.0026 and 0.0046 respectively.The experimental results show that the hybrid deep convolutional network can effectively perform super-resolution reconstruction of the image.
作者
胡雪影
郭海儒
朱蓉
HU Xueying;GUO Hairu;ZHU Rong(College of Computer Science and Technology,Henan Polytechnic University,Jiaozuo Henan 454000,China;College of Mathematics and Information Engineering,Jiaxing University,Jiaxing Zhejiang 314000,China)
出处
《计算机应用》
CSCD
北大核心
2020年第7期2069-2076,共8页
journal of Computer Applications
基金
浙江省重点研发计划项目(2019C03099)
浙江省自然科学基金资助项目(LY19F020017)。
关键词
图像超分辨率重建
图像特征去噪
混合深度卷积网络
反卷积
空洞卷积
image super-resolution reconstruction
image feature denoising
hybrid deep convolutional network
deconvolution
dilated convolution