强激光与粒子束, 2012, 24 (9): 2215, 网络出版: 2012-09-12   

基于BP神经网络的闪光照相图像复原

Restoration method for flash radiographic images based on BP neural network
作者单位
中国工程物理研究院 流体物理研究所, 四川 绵阳 621900
摘要
针对闪光照相系统模糊较大、成像信噪比较低的问题,提出了一种基于BP神经网络的闪光照相图像复原方法。该方法利用BP神经网络的泛化能力,用样本图像对网络进行训练,建立退化图像与真实图像之间的非线性映射关系,然后将待复原图像分区,利用训练好的BP神经网络对待复原图像的边界区域进行复原处理。数值试验表明,在系统点扩展函数未知的情况下,该算法能较好再现图像边缘信息,复原出的图像在信噪比和视觉方面都有较大提高。
Abstract
A BP neural network based image restoration algorithm is proposed against the blur of flash radiographic images with low signal-to-noise ratios. Firstly the degraded image and the sample image are both divided into the edge part and the smooth part. Secondly the nonlinear mapping relationship between the degraded image and its original image is established by training the BP neural network which has the ability of learning, remembrance and generalizing with the edge part of the sample image. Finally the edge part of the degraded image could be restored by the trained neural network. Numerical results show that this method could restore the image information near edges when the systematic point-spread function is unknown, and the restored image is greatly improved in the signal-to-noise ratio and in the visual.
参考文献

[1] Scarpetti R D, Nath S, Barraza J, et al. Status of the DARHT 2nd axis accelerator at the Los Alamos National Laboratory[C]//Particle Accelerator Conference. 2007:831-835.

[2] 刘军,刘进,施将君. FTO客体3 m闪光照相的Monte-Carlo研究[J]. 强激光与粒子束,2004,16(9):1210-1214.(Liu Jun, Liu Jin, Shi Jiangjun. Monte-Carlo research of flash radiography at 3 m to the target. High Power Laser and Particle Beams,2004,16(9):1210-1214)

[3] 刘军,刘进,管永红,等.闪光照相中MeV级网栅的设计[J]. 强激光与粒子束,2011,23(8):2047-2051.(Liu Jun, Liu Jin, Guan Yonghong, et al. The design of MeV anti-scatter grid in flash radiography. High Power Laser and Particle Beams,2011,23(8):2047-2051)

[4] 景越峰,张小琳,管永红. 基于约束共轭梯度的高能闪光照相图像复原算法[J].强激光与粒子束,2009,21(2):277-280.(Jing Yuefeng, Zhang Xiaolin, Guan Yonghong. Constrained conjugate gradient algoritham for image restoration in high-energy radiography. High Power Laser and Particle Beams,2009,21(2):277-280)

[5] Hornik K M, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators[J]. Neural Networks,1989,2(2):359-366.

[6] 王辉,杨杰,黎明,等. 一种基于神经网络的图像复原方法[J].红外与激光工程,2006,37(10):121-125.(Wang Hui, Yang Jie, Li Ming, et al. Image restoration method based on neural network. Infared and Laser Engineering, 2006,37(10):121-125)

[7] 尚钢,钟珞,陈立耀. 神经网络结构与参数选取[J].武汉工业大学学报,1997,19(2):108-110.(Shang Gang, Zhong Luo, Chen Liyao. Discussion about BP neural network structure and choice of samples training parameter. Journal of Wuhan University of Technology,1997,19(2):108-110)

[8] Lera G,Pinzolas M. Neighborhood based Levenberg-Marquardt algorithm for neural network training[J]. IEEE Trans on Neural Networks, 2002,13(5):1200-1203.

景越峰, 刘军, 管永红. 基于BP神经网络的闪光照相图像复原[J]. 强激光与粒子束, 2012, 24(9): 2215. Jing Yuefeng, Liu Jun, Guan Yonghong. Restoration method for flash radiographic images based on BP neural network[J]. High Power Laser and Particle Beams, 2012, 24(9): 2215.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!