首页 | 本学科首页   官方微博 | 高级检索  
     

基于深度特征学习的图像超分辨率重建
引用本文:胡长胜, 詹曙, 吴从中. 基于深度特征学习的图像超分辨率重建. 自动化学报, 2017, 43(5): 814-821. doi: 10.16383/j.aas.2017.c150634
作者姓名:胡长胜  詹曙  吴从中
作者单位:合肥工业大学计算机与信息学院 合肥 230009
基金项目:国家自然科学基金(61371156),安徽省科技攻关项目基金(1401B042019),中科院自动化所复杂系统管理与控制国家重点实验室开放课题(20130107)资助
摘    要:基于学习的图像超分辨率(Super-resolution,SR)算法利用样本先验知识来重建图像,相较于其他重建方法拥有明显的优势,也是近年来研究的热点.论文首先分析了影响图像重建质量的因素,然后对基于卷积神经网络的图像超分辨率重建算法(Super-resolution convolutional neural network,SRCNN)提出了两点改进:我们用随机线性纠正单元(Randomized rectified linear unit,RReLU)去避免原有网络学习中对图像某些重要的信息过压缩,同时我们用NAG(Nesterov's accelerated gradient)方法去加速网络的收敛并且避免了网络在梯度更新的时候产生较大的震荡.最后通过实验验证了我们改进网络可以获得更好的主观视觉评价和客观量化评价.

关 键 词:超分辨率   图像复原   深度学习   卷积神经网络   特征映射
收稿时间:2015-10-13

Image Super-resolution Based on Deep Learning Features
HU Chang-Sheng, ZHAN Shu, WU Cong-Zhong. Image Super-resolution Based on Deep Learning Features. ACTA AUTOMATICA SINICA, 2017, 43(5): 814-821. doi: 10.16383/j.aas.2017.c150634
Authors:HU Chang-Sheng  ZHAN Shu  WU Cong-Zhong
Affiliation:School of Computer and Information, Hefei University of Technology, Hefei 230009
Abstract:Learning-based image super-resolution method is a research hotspot in recent years which uses prior knowledge of sample to reconstruct the image and has obvious advantages over other reconstruction methods. In this paper, we first analyze the factors of reconstructed image quality. Then we use randomized rectified linear unit (RReLU) to solve the problem of over compression in the original network. Besides, Nesterov's accelerated gradient (NAG) is invoked to accelerate convergence and avoid large oscillations. Finally, we conduct a quantitative experiments to prove the validity of the proposed algorithm.
Keywords:Super-resolution (SR)  image restoration  deep learning  convolution neural network (CNN)  feature map
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号