[1]陈北京,戴慧,刘全升,等.基于四元数表示的彩色图像泊松噪声去噪[J].东南大学学报(自然科学版),2013,43(4):717-723.[doi:10.3969/j.issn.1001-0505.2013.04.009]
 Chen Beijing,Dai Hui,Liu Quansheng,et al.Poisson noise removal for color images using quaternion representation[J].Journal of Southeast University (Natural Science Edition),2013,43(4):717-723.[doi:10.3969/j.issn.1001-0505.2013.04.009]
点击复制

基于四元数表示的彩色图像泊松噪声去噪()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
43
期数:
2013年第4期
页码:
717-723
栏目:
计算机科学与工程
出版日期:
2013-07-20

文章信息/Info

Title:
Poisson noise removal for color images using quaternion representation
作者:
陈北京12戴慧3刘全升4舒华忠5
1南京信息工程大学计算机与软件学院, 南京 210044; 2南京信息工程大学江苏省网络监控工程中心, 南京 210044; 3南京工程学院计算机工程学院, 南京 210013; 4南布列塔尼大学应用数学实验室, 法国瓦纳 56017; 5东南大学影像科学与技术实验室, 南京 210096
Author(s):
Chen Beijing12 Dai Hui3 Liu Quansheng4 Shu Huazhong5
1School of Computer and Software, Nanjing Univ of Information Sci and Tech, Nanjing 210044, China
2Jiangsu Engineering Center of Network Monitoring, Nanjing Univ  of Information Sci and Tech, Nanjing 210044, China
3School of Computer Engineering, Nanjing Institute of Technology, Nanjing 210013, China
4Laboratoire de Mathématiques de Bretagne Atlantique, Université de Bretagne-Sud, Vannes 56017, France
5Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China
关键词:
彩色图像去噪 泊松噪声 四元数 非局部均值滤波器 最优权值滤波器
Keywords:
color image denoising Poisson noise quaternion non-local means filter optimal weights filter
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2013.04.009
摘要:
为了整体处理彩色图像,提出了一种基于四元数的去除泊松噪声的加权平均滤波器.首先,基于彩色图像四元数表示法,将一幅彩色图像表示为一个纯四元数矩阵,并利用四元数代数理论定义了重建图像和原始图像之间的四元数均方误差;然后,结合非局部均值滤波的基本思想,采用拉格朗日乘数法推导出使QMSE紧上界最小的加权系数;最后,基于这些最优加权系数,对四元数表示的像素值进行加权平均,构造出四元数最优权值非局部均值滤波器,并将其应用于彩色图像泊松噪声去噪.针对常用标准图像的对比实验结果表明,所提的滤波器优于现有的四元数滤波器以及传统的基于向量方法的滤波器和基于分量独立处理方法的滤波器.
Abstract:
In order to process color images holistically, a quaternion weighted mean filter for Poisson noise removal in color images is presented. First, a color image is represented by a pure quaternion matrix by using the quaternion representation of color images. After that, the quaternion mean square error(QMSE)between the restored color image and the original one is defined based on the algebra of quaternions. Then, combining with the essential idea of the non-local means filter, the optimal weights for minimizing the tight bound of QMSE are obtained by using the method of Lagrange multipliers. Finally, the weighted average of the observed quaternion representation is obtained, and a quaternion optimal weights non-local means filter(QOWNLMF)for Poisson noise removal for color image is constructed by using the optimal weights. The comparative experiment results of commonly used standard images demonstrate that the proposed filter performs better than the existing quaternion filters and the conventional vector-based filter and component-wise filter.

参考文献/References:

[1] Lukac R, Smolka B, Martin K, et al. Vector filtering for color imaging[J]. IEEE Signal Processing Magazine, 2005, 22(1): 74-86.
[2] Jin L H, Liu H, Xu X Y, et al. Quaternion-based color image filtering for impulsive noise suppression[J]. Journal of Electronic Imaging, 2010, 19(4): 043003-1-043003-12.
[3] Geng X, Hu X G, Xiao J. Quaternion switching filter for impulse noise reduction in color image[J]. Signal Processing, 2012, 92(1): 150-162.
[4] Subakan O N, Vemuri B C. A quaternion framework for color image smoothing and segmentation[J]. International Journal of Computer Vision, 2011, 91(3): 233-250.
[5] Hamilton W R. Elements of quaternions[M]. London: Longmans Green, 1866.
[6] Jin L H, Li D H. An efficient color-impulse detector and its application to color images[J]. IEEE Signal Processing Letters, 2007, 14(6): 397-400.
[7] Lei Y J, Chen C J, Lang F N. Quaternion singular value decomposition approach to color image denoising[C]//Proceedings of 2008 IEEE International Joint Conference on Neural Networks. Hong Kong, China, 2008: 131-136.
[8] Reddy B D V, Prasad D T J. Frequency domain filtering of colour images using quaternion Fourier transforms[J]. International Journal of Computer Science and Technology, 2010, 1(2): 46-52.
[9] Shi L L, Funt B. Quaternion color texture segmentation[J]. Computer Vision and Image Understanding, 2007, 107(1): 88-96.
[10] Chen B J, Shu H Z, Zhang H, et al. Quaternion Zernike moments and their invariants for color image analysis and object recognition[J]. Signal Processing, 2012, 92(2): 308-318.
[11] Tsui T K, Zhang X P, Androutsos D. Color image watermarking using multidimensional Fourier transforms[J]. IEEE Transactions on Information Forensics and Security, 2008, 3(1): 16-28.
[12] Makitalo M, Foi A. Optimal inversion of the Anscombe transformation in low-count Poisson image denoising[J]. IEEE Transactions on Image Processing, 2011, 20(1): 99-109.
[13] Buades A, Coll B, Morel J M. A non-local algorithm for image denoising[C]//Proceedings of 2005 IEEE International Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA, 2005: 60-65.
[14] Buades A, Coll B, Morel J M. Non-local means denoising[EB/OL].(2011-09-13)[2012-12-10]. http://www.ipol.im/pub/art/2011/bcm_nlm/.
[15] Jin Q, Grama I, Liu Q. Removing Poisson noise by optimization of weights in non-local means[C]//Proceedings of 2012 IEEE Symposium on Photonics and Optoelectronics. Shanghai, China, 2012: 1-4.
[16] Jin Q, Grama I, Liu Q. A new Poisson noise filter based on weights optimization[EB/OL].(2012-01-28)[2012-12-01]. http://arxiv.org/abs/1201.5968.

备注/Memo

备注/Memo:
作者简介: 陈北京(1981—),男,博士,讲师, nbutimage@126.com.
基金项目: 国家重点基础研究发展计划(973计划)资助项目(2011CB707904)、国家自然科学基金资助项目(61073138,61103141,61105007,61173141,61271312,61272421)、教育部博士点基金资助项目(20110092110023)、江苏省高校自然科学研究基金资助项目(13KJB520015)、江苏省高校优势学科建设工程资助项目、 南京信息工程大学科研基金资助项目(20110430).
引文格式: 陈北京,戴慧,刘全升,等.基于四元数表示的彩色图像泊松噪声去噪[J].东南大学学报:自然科学版,2013,43(4):717-723. [doi:10.3969/j.issn.1001-0505.2013.04.009]
更新日期/Last Update: 2013-07-20