基于BP神经网络的超分辨率图像重建

Journal of Systems Engineering and Electronics ›› 2009, Vol. 31 ›› Issue (7): 1746-1749,1781.

基于BP神经网络的超分辨率图像重建

朱福珍, 李金宗, 李冬冬

哈尔滨工业大学图像信息与工程研究所, 黑龙江, 哈尔滨, 150001

收稿日期:2008-05-13 修回日期:2008-10-07 出版日期:2009-07-20 发布日期:2010-01-03
作者简介:朱福珍(1978- ),女,博士研究生,主要研究方向为数字图像处理,神经网络图像超分辨重建技术.E-mail:zhufuzhen_1978@163.com

Reconstruction of super-resolution image based on BP neural network

ZHU Fu-zhen, LI Jin-zong, LI Dong-dong

Inst. of Image Information Technology and Engineering, Harbin Inst. of Technology, Harbin 150001, China

Received:2008-05-13 Revised:2008-10-07 Online:2009-07-20 Published:2010-01-03

摘要/Abstract

摘要： 针对卫星图像成像过程中成像装置存在极限,导致图像分辨率低的问题,提出了基于神经网络的图像超分辨率重建(neural networks super-resolution reconstruction,NNSR)方法。该方法利用误差反向传播神经网络(back propagation neural networks,BPNN)对样本图像进行学习和训练,利用图像退化模型获取学习样本,采用向量映射加速BP神经网络的收敛,充分融合了低分辨率序列图像中的冗余信息。通过对训练好的神经网络分别进行样本仿真实验和泛化实验,验证了这种图像超分辨率重建方法的有效性。

Abstract: The reconstruction of the super-resolution image based on neural networks(NN) is proposed to resolve the problem of image low spatial resolution because of the limitation of imaging devices.An error back-propagation(BP) algorithm is used to learn and train sample images in order to combine the redundancy information of low spatial resolution images sequences.Learning samples are acquired according to the image observation model.Vector mapping is established to speed up the convergence of NN.Simulation and generalization tests are carried on the well-trained NN respectively,and the reconstruction results with higher spatial resolution images verify the effectiveness and validity of BPNN based on vector mapping in the reconstruction of the super-resolution image.

中图分类号:

TP183

朱福珍, 李金宗, 李冬冬. 基于BP神经网络的超分辨率图像重建[J]. Journal of Systems Engineering and Electronics, 2009, 31(7): 1746-1749,1781.

ZHU Fu-zhen, LI Jin-zong, LI Dong-dong. Reconstruction of super-resolution image based on BP neural network[J]. Journal of Systems Engineering and Electronics, 2009, 31(7): 1746-1749,1781.

参考文献

[1] Sung Cheol Park,Min Kyu Park,Moon Gi Kang.Super-resolution image reconstruction; A technical overview[J].IEEE Signal Processing Magazine,2003,21:1053-5888.
[2] Huang T S,Tsai R Y.Multi-frame image restoration and regis-trationCC]//Advances in Computer Vision and Image Processing,1984(1):317-339.
[3] Kim S P,Bose N K,Valenzuela H M.Recursive reconstruction of high resolution image from noisy undersampled multiframes[J].IEEE Trans.on Acoust,Speech,Signal Processing,1990,6(38),1013-1027.
[4] Ur H,Gross D.Improved resolution from subpixel shifted pic tures[J].CVGIP:Graphical Models Image Processing,1992,2(54):181-186.
[5] Irani M,Peleg S.Improving resolution by image registration[J].CVGIP:Graphical Model Image Processing,1991,3(53):231-239.
[6] Cheeseman P,Kanefsky B,Kraft R,et al.Superresolved sur-face reconstruction from multiple images[R].NASA Technical Report FIA,1994:94-12.
[7] Tom B C,Katsaggelos A K.Reconstruction of a high-resolution image by simultaneous registration,restoration,and interpola-tion of low-resolution images[C]//IEEE International Confer-ence Image Processing,Washington DC,1995.
[8] Patti A J,Sezan M I,Tekalp A M.superresolution video recon-struction with arbitrary sampling lattices and nonzero aperture time[J].IEEE Trans.on Image Processing,1997,6(8):1064-1076.
[9] Patti A J,Altunbasak Y.Artifact reduction for set theoretic superresolution image reconstruction with edge adaptive constraints and higher-order interpolants[J].IEEE Trans.on Image Processing,2001,10(1):179-186.
[10] Elad M,Feuer A.superresolution restoration of an image sequence:adaptive filtering approach[J].IEEE Trans.on Image Processing,1999,6(3):387-395.
[11] 刘梅,刘慧念,刘伟东,等.一种基于神经网络的超分辨率图像重构方法[J].哈尔滨工业大学学报,2003,35(6):707-710.
[12] Sun Y.Hopfield neural network based on algorithms for image restoration and reconstruction-Part I:Algorithms and simulations[J].IEEE Trans.on Signal Processing,2000,48(7):2105-2118.
[13] Yao Lu,Minoru Inamura,Maria del Carmen Valdes.Super resolution of the undersampled and subpixel shifted image sequence by a neural network[J].Imaging Systems and Technology,2004,1(14):8-15.
[14] 许东,吴铮.基于Matlab的系统分析与设计--神经网络[M].西安:西安电子科技大学出版社,2003.
[15] Tom M Mitchell.机器学习[M].曾华军,张银奎,译.北京:机械工业出版社,2003.