? 基于块匹配三维滤波和卷积神经网络的图像去噪
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2018, Vol. 33 Issue (4) :838-848    DOI: 10.1007/s11390-018-1859-7
Special Issue on Software Engineering for High-Confidence Systems << Previous Articles | Next Articles >>
基于块匹配三维滤波和卷积神经网络的图像去噪
Bei-Ji Zou1,2, Yun-Di Guo1,3, Qi He1,3, Ping-Bo Ouyang1,3, Ke Liu2, Zai-Liang Chen1,3,*
1 School of Information Science and Engineering, Central South University, Changsha 410083, China;
2 Center for Information and Automation of China Nonferrous Metals Industry Association, Changsha 410011, China;
3 Center for Ophthalmic Imaging Research, Central South University, Changsha 410083, China
3D Filtering by Block Matching and Convolutional Neural Network for Image Denoising
Bei-Ji Zou1,2, Yun-Di Guo1,3, Qi He1,3, Ping-Bo Ouyang1,3, Ke Liu2, Zai-Liang Chen1,3,*
1 School of Information Science and Engineering, Central South University, Changsha 410083, China;
2 Center for Information and Automation of China Nonferrous Metals Industry Association, Changsha 410011, China;
3 Center for Ophthalmic Imaging Research, Central South University, Changsha 410083, China

摘要
参考文献
相关文章
Download: [PDF 6419KB]  
摘要 基于快匹配三维滤波的方法再图像去噪任务种取得了巨大的成功,然而人工设定的滤波参数不能很好地描述有噪声图像与无噪声图像地映射模型。本文介绍通过卷积网络完成三位滤波步骤,学习一个更为拟合的去噪模型。利用可学习模型,先验知识能够被利用以实现更好的有噪图像到清晰图像的映射。这个快匹配与卷积神经网络结合的模型能够对不同形状和强度的噪声图像取得较好去噪效果,特别是具有较高强度噪声的图像。实验表明本方法在较强噪声图像(σ>40)中取得了较高的峰值信噪比,且在对比的集中方法中具有最好的视觉质量。
关键词块匹配   卷积神经网络   去噪   三维滤波     
Abstract: Block matching based 3D filtering methods have achieved great success in image denoising tasks. However, the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network (CNN) for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model (BMCNN) could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio (PSNR) when denoising images with high noise levels (σ > 40), and the best visual quality when denoising images with all the tested noise levels.
Keywordsblock matching   convolutional neural network (CNN)   denoising   3D filtering     
Received 2017-06-22;
本文基金:

This research was supported by the National Natural Science Foundation of China under Grant Nos. 61573380 and 61672542, and Fundamental Research Funds for the Central Universities of China under Grant No. 2016zzts055.

通讯作者: Zai-Liang Chen,E-mail:zailiangchencs@gmail.com     Email: zailiangchencs@gmail.com
About author: Bei-Ji Zou received his B.S. degree in computer software from Zhejiang University, Hangzhou, in 1982, and his M.S. and Ph.D. degrees in computer science and technology from Tsinghua University, Beijing, in 1984, and Hunan University, Changsha, in 2001, respectively. He joined the School of Computer and Communication at Hunan University, Changsha, in 1984, where he became an associate professor in 1997, and a professor in 2001. He served as the vice dean there since 1997. He is currently a professor and served as the dean of the School of Information Science and Engineering in Central South University, Changsha. His research interest is focused on computer graphics, image processing, and virtual reality technology. Until now he has published more than 100 papers in journals.
引用本文:   
Bei-Ji Zou, Yun-Di Guo, Qi He, Ping-Bo Ouyang, Ke Liu, Zai-Liang Chen.基于块匹配三维滤波和卷积神经网络的图像去噪[J]  Journal of Computer Science and Technology , 2018,V33(4): 838-848
Bei-Ji Zou, Yun-Di Guo, Qi He, Ping-Bo Ouyang, Ke Liu, Zai-Liang Chen.3D Filtering by Block Matching and Convolutional Neural Network for Image Denoising[J]  Journal of Computer Science and Technology, 2018,V33(4): 838-848
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-018-1859-7
Copyright 2010 by Journal of Computer Science and Technology