摘要
超分辨率图像可以提供更丰富的纹理细节信息,在机器视觉应用领域中占有重要的地位,已成为机器视觉领域的一个研究热点。利用深度学习技术,设计一个深度卷积神经网络,实现从低分辨率图像到高分辨率图像的非线性映射,从而实现图像的超分辨率重建。通过实验,将所设计的网络模型与一些前沿的方法进行了定性和定量的比较,实验结果表明设计的网络模型具有明显的优越性。
Single image super-resolution (SISR) has attracted great attentions due to it can offer more details that may play a critical role in various machine vision tasks. In this paper, a deep convolutional neural networks is proposed to address the SISR problem via the deep learning technique, which has a powerful capability for achieving the non-linear mapping between low and high resolution images. We compare our method with some state-of-the-arts in the experimental section. The results demonstrate that the proposed model achieves a notable improvement in terms of both quantitative and qualitative measurements.
作者
韦玉婧
林贵敏
邱立达
张腾
WEI Yujing;LIN Guimin;QIU Lida;ZHANG Teng(College of Physics and Electronic Information Engineering,Minjiang University, Fuzhou, Fujian 350108, China)
出处
《闽江学院学报》
2019年第2期70-75,共6页
Journal of Minjiang University
基金
闽江学院大学生校长基金项目(103952018106
103952018122)
关键词
深度学习
卷积神经网络
超分辨率
deep learning
convolutional neural networks
super-resolution
