南京信息工程大学学报2017，Vol.9Issue(6)：669-674,6.DOI:10.13878/j.cnki.jnuist.2017.06.012
基于边缘指导的双通道卷积神经网络 单图像超分辨率算法
Edge guided dual-channel convolutional neural network for single image super resolution algorithm
摘要
Abstract
At present, although the super-resolution ( SR ) reconstruction algorithm based on the Convolutional Neural Network ( CNN) has achieved great success,it cannot well reconstruct the high-frequency texture of the image.As a result,there exists obvious shake in local edge of the high-resolution ( HR) image. We present an edge guided dual-channel CNN SR reconstruction algorithm integrated with Morphological Component Analysis ( MCA) . The low-resolution ( LR) image to be processed is decomposed into texture part and structure part by MCA,then the texture part and the original LR image form a dual channel together,which is then input into the modified network structure to reconstruct the HR texture part.The reconstruction loss of both the HR image and HR texture are chosen simultaneously for training.As for post-processing step,we perform histogram matching between our network output and the LR input to strengthen the visual effect and apply an iterative back projection refinement to improve the PSNR.As shown in experiment results,this method with dual-channel input can restore texture details of the image, especially restore the image with rich texture.关键词
超分辨率/卷积神经网络/形态学成分分析/双通道输入Key words
super resolution/convolutional neural network/morphological component analysis ( MCA )/dual-channel input分类
信息技术与安全科学引用本文复制引用
李春平,周登文,贾慧秒..基于边缘指导的双通道卷积神经网络 单图像超分辨率算法[J].南京信息工程大学学报,2017,9(6):669-674,6.基金项目
国家自然科学基金(61372184) （61372184）
北京市自然科学基金(4162056) （4162056）
