强激光与粒子束, 2013, 25 (3): 751, 网络出版: 2013-03-05   

基于神经网络的闪光照相网栅图像修补

Inpainting method for flash radiographic anti-scatter grid image based on neural networks
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
提出了一种基于径向基函数(RBF)神经网络的闪光照相网栅图像修补算法, 该方法采用滑动窗口方法将待修补的网栅图像分为若干子块, 然后在每个子图像内分别引入RBF神经网络, 将栅孔内图像作为已知数据计算RBF网络参数, 并以此对每个子图像进行修补, 数值试验表明, 该算法能较好地再现图像边缘信息, 修复的图像在信噪比和视觉方面都优于线性插值和样条插值的结果。
Abstract
To solve the problem of flash radiographic anti-scatter grid image inpainting, a radial basis function (RBF) neural network based image inpainting algorithm is proposed. First the anti-scatter grid image is divided into a series of blocked images. Then the weights of the RBF network are estimated and a continuous function is constructed in each blocked image, and with them the pixels of missing information can be filled in. The experimental results show that the new algorithm has better general performance in inpainting quality and boundary maintenance compared with the linear interpolation and spline interpolation method.
参考文献

[1] 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)

[2] 施将君, 李必勇, 刘军, 等. 闪光照相中散射照射量的解析分析[J]. 强激光与粒子束, 2006, 18(7):1211-1214.(Shi Jiangjun, Li Biyong, Liu Jun, et al. Analystic determination of scatter exposure for radiography.High Power Laser and Particle Beams, 2006, 18(7):1211-1214)

[3] 李必勇, 施将君, 刘进, 等. 闪光照相系统的散射分布与降散射的数值模拟[J].强激光与粒子束, 2005, 17(5):788-792.(Li Biyong, Shi Jiangjun, Liu Jin, et al. Numerical simulation of scattered exposure and reduced scatter in flash radiography system. High Power Laser and Particle Beams, 2005, 17(5):788-792)

[4] 肖智强, 刘军, 胡八一, 等. 高能闪光照相中陡坡准直体成像性能实验研究[J]. 核电子学与探测器技术, 2007, 27(3):512-515.(Xiao Zhiqiang, Liu Jun, Hu Bayi, et al. Experimental research of the performance of graded collimators in high-energy flash X-ray radiography. Nuclear Electronics and Detection Technology, 2007, 27(3):512-515)

[5] 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)

[6] Bertalmio M, Bertozzi A L, Sapiro G, et al. Navier-Stokes, fluid dynamics, and image and video inpainting[C]//Proc of the International Conference on Computer Vision and Pattern Recognition. 2001, 1:355-362.

[7] Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12(7):629-639.

[8] 景越峰, 张小琳, 管永红.基于偏微分方程的闪光照相图像修补算法[J].强激光与粒子束, 2010, 22(2):383-387.(Jing Yuefeng, Zhang Xiao lin, Guan Yonghong. Radiography image inpainting algorithm based on partial differential equations.High Power Laser and Particle Beams, 2010, 22(2):383-387)

[9] Chan T, Shen J. Nontexture inpainting by curvature-driven diffusions[J].Journal of Visual Communication and Image Representation, 2001, 12(3):436-449.

[10] 张红英, 彭启琮, 吴亚东. 数字破损图像的非线性各向异性扩散修补算法[J]. 计算机辅助设计与图形学学报, 2006, 18(10):1541-1546.(Zhang Hongying, Peng Qicong, Wu Yadong. Digital image inpainting algorithm for damaged images based on nonlinear anisotropic diffusion. Journal of Computer-Aided Design and Computer Graphics, 2006, 18(10): 1541-1546)

[11] Bianchini M, Frasconi P. Learning without local minima in radial basis function networks[J].IEEE Trans on Neural Networks, 1995, 6(3):749-756.

[12] 牛丽红, 倪国强, 苏秉华. 基于RBF 神经网络的图像融合复原方法研究[J]. 光子学报, 2006, 35(2):316-320.(Niu Lihong, Ni Guoqiang, Su Binghua. RBF neural network based image fusion restoration approach.Acta Photonica Sinica, 2006, 35(2):316-320)

景越峰, 刘军, 管永红. 基于神经网络的闪光照相网栅图像修补[J]. 强激光与粒子束, 2013, 25(3): 751. Jing Yuefeng, Liu Jun, Guan Yonghong. Inpainting method for flash radiographic anti-scatter grid image based on neural networks[J]. High Power Laser and Particle Beams, 2013, 25(3): 751.

本文已被 5 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!