基于迭代重加权的非刚性图像配准

韩雨; 王卫卫; 冯象初

doi:10.3724/SP.J.1004.2011.01059

基于迭代重加权的非刚性图像配准

doi: 10.3724/SP.J.1004.2011.01059

1.
西安电子科技大学理学院应用数学系西安 710071

详细信息

通讯作者:
韩雨西安电子科技大学理学院应用数学系博士研究生. 主要研究方向为图像配准和分割.E-mail: hany_xidian@126.com

计量
- 文章访问数: 2347
- HTML全文浏览量: 80
- PDF下载量: 1148
- 被引次数: 0
出版历程
- 收稿日期: 2010-09-28
- 修回日期: 2011-04-09
- 刊出日期: 2011-09-20

Iteratively Reweighted Method Based Nonrigid Image Registration

1.
Department of Applied Mathematics, School of Science, Xidian University, Xi'an 710071

摘要

摘要: 非刚性图像配准问题是当今重要的研究课题. 本文提出一类基于能量最小化方法的非刚性图像配准模型, 其中包括单模态和多模态两个模型. 在单模态模型中,正则项采用迭代重加权的L2范数度量, 一方面克服了迭代收敛不同步的问题, 另一方面使新模型既能保持图像的边缘几何结构, 又能避免块效应的产生. 在多模态模型中, 不同模态的图像被转化为同一模态进行处理, 提高了配准的效率. 在模型求解方面, 利用算子分裂和交替最小化的方法, 将原问题转化为阈值和加性算子分裂的迭代格式进行求解. 数值实验表明, 本文的方法对含噪以及变形较大的图像都能实现较好的配准.
- 图像配准 /
- 光流场 /
- 多模态 /
- 互信息 /
- 算子分裂
Abstract: Nowadays, the nonrigid image registration problem has been an important research topic. This paper proposes an energy-based framework of the nonrigid image registration, including both a one-modality model and a multi-modality model. In the one-modality model, the iteratively reweighted L2 norm is used to measure the regularization term, which brings out two advantages. Firstly, it avoids the imbalance problem of the converging speed in different regions. Secondly, it preserves the important geometric structures of an image while restrains the staircase effect. In the multi-modality model, images obtained from different modalities are converted into the one-modality ones, and then methods, handling the one-modality problems can be used to deal with the multi-modality problems. By exploiting the techniques of the operator splitting and the alternative minimization, we solve our model by shrinking and additional operator splitting (AOS). Numerical results demonstrate that the proposed method performs well even for noisy images and images with large deformation.
- Image registration /
- optical flow field /
- multi-modality /
- mutual information /
- operator splitting

HTML全文

参考文献(1)

[1]

Thirion J. Image matching as a diffusion process: an analogy with Maxwell's demons. Medical Image Analysis, 1998, 2(3): 243-260[2] Wang H, Dong L, O'Daniel J, Mohan R, Garden AS, Ang K K. Validation of an accelerated "demons" algorithm for deformable image registration in radiation therapy. Physics in Medicine and Biology, 2005, 50(12): 2887-2905[3] Pock T, Urschler M, Zach C, Beichel R, Bischof H. A duality based algorithm for TV-L_1 optical flow image registration. Medical Image Computing and Computer-Assisted Intervention, 2007, 4792: 511-518[4] Bai Xiao-Jing, Chen Yun-Jie, Sun Huai-Jiang. An improved optical flow model for brain image registration. Computer-Aided Design and Computer Graphics, 2008, 20(3): 349-355(白小晶, 陈允杰, 孙怀江. 基于改进光流场模型的大脑图像配准. 计算机辅助设计与图形学学报, 2008, 20(3): 349-355)[5] Lu W, Chen M, Olivera G, Ruchala K J, Mackie T R. Fast free-form deformable registration via calculus of variations physical. Physics in Medicine and Biology, 2004, 49(14): 3067-3087[6] Viola P, Wells W. Alignment by maximization of mutual information. International Journal of Computer Vision, 1997, 24(2): 137-154[7] Pluim J, Maintz J, Viergever M. Mutual-information-based registration of medical images: a survey. IEEE Transactions on Medical Imaging, 2003, 22(8): 986-1004[8] Loeckx D, Slagmolen P, Maes F, Vandermeulen D, Suetens P. Nonrigid image registration using conditional mutual information. IEEE Transactions on Medical Imaging, 2010, 29(1): 19-29[9] Hahn D A, Daum V, Hornegger J. Automatic parameter selection for multimodal image registration. IEEE Transactions on Medical Imaging, 2010, 29(5): 1140-1155[10] Zhang Shao-Min, Zhi Li-Jia, Zhao Da-Zhe, Zhao Hong, Yang Jin-Zhu. Multi-modality medical image registration based on regional joint Renyi entropy. Acta Electronica Sinica, 2009, 37(10): 2321-2325(张少敏, 支力佳, 赵大哲, 赵宏, 杨金柱. 基于区域联合Renyi熵的多模医学图像配准. 电子学报, 2009, 37(10): 2321-2325)[11] Niu Li-Pi, Mao Shi-Yi, Chen Wei. Image registration based on Hausdorff distance. Journal of Electronics and Information Technology, 2007, 29(1): 36-38(牛力丕, 毛士艺, 陈炜. 基于Hausdorff距离的图像配准研究. 电子与信息学报, 2007, 29(1): 36-38)[12] Wang An-Na, Zhang Xin-Hua, Gu Zhao-Wei, Pan Bo. A medical image registration algorithm based on revised Hausdorff distance. Acta Electronica Sinica, 2008, 36(11): 2248-2250(王安娜, 张新华, 谷召伟, 潘博. 基于改进Hausdorff测度的医学图像配准算法. 电子学报, 2008, 36(11): 2248-2250)[13] Zhang Xiu-Wei, Zhang Yan-Ning, Yang Tao, Zhang Xin-Gong, Shao Da-Pei. Automatic visual-thermal image sequence registration based on co-motion. Acta Automatica Sinica, 2010, 36(9): 1221-1231(张秀伟, 张艳宁, 杨涛, 张新功, 邵大培. 基于Co-motion的可见光--热红外图像序列自动配准算法. 自动化学报, 2010, 36(9): 1221-1231)[14] Zhang Hong-Ying, Zhang Jia-Wan, Sun Ji-Zhou. Non-rigid medical image registration based on improved demons algorithm. Optics and Precision Engineering, 2007, 15(1): 145-150(张红颖, 张加万, 孙济洲. 改进Demons算法的非刚性医学图像配准. 光学精密工程, 2007, 15(1): 145-150)[15] Kroon D J, Slump C H. MRI modalitiy transformation in demon registration. In: Proceedings of the IEEE International Symposium on Biomedical Imaging. Boston, USA: IEEE, 2009. 963-966[16] Lin Xiang-Bo, Qiu Tian-Shuang, Ruan Su. Research on the topology preservation of the demons non-rigid registration algorithm. Acta Automatica Sinica, 2010, 36(1): 180-183(林相波, 邱天爽, 阮素. Demons非刚性配准算法拓扑保持性的研究. 自动化学报, 2010, 36(1): 180-183)[17] Zhang L, Dong W S, Zhang D, Shi G M. Two-stage image denoising by principal component analysis with local pixel grouping. Pattern Recognition, 2010, 43(4): 1531-1549[18] Feng Xiang-Chu, Wang Wei-Wei. Variational and PDE Based Approaches in Image Processing. Beijing: Science Press, 2009(冯象初, 王卫卫. 图像处理的变分和偏微分方程方法. 北京: 科学出版社, 2009)[19] Lysaker M, Lundervold A, Tai X C. Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time. IEEE Transactions on Image Processing, 2003, 12(12): 1579-1590[20] Daubechies I, DeVore R, Fornasier M, Gunturk C S. Iteratively re-weighted least squares minimization for sparse recovery. Communications on Pure and Applied Mathematics, 2010, 63(1): 1-38[21] Candues E J, Wakin M B, Boyd S P. Enhancing sparsity by reweighted L_1 minimization. Journal of Fourier Analysis and Applications, 2008, 14(5-6): 877-905[22] Nikolova M, Ng M K, Zhang S Q, Ching W K. Efficient reconstruction of piecewise constant images using nonsmooth nonconvex minimization. SIAM Journal on Imaging Sciences, 2008, 1(1): 2-25[23] Weickert J, Romeny B M, Viergever M A. Efficient and reliable schemes for nonlinear diffusion filtering. IEEE Transactions on Image Processing, 1998, 7(3): 398-410[24] Shi Yong-Gang, Zou Mou-Yan. Performance comparison of statistics based similarity measures for image registration. Chinese Journal of Computers, 2004, 27(9): 1279-1283(时永刚, 邹谋炎. 图像配准中统计型相似性测度的比较与分析. 计算机学报, 2004, 27(9): 1279-1283)[25] Baker S, Scharstein D, Lewis J P, Roth S, Black M, Szeliski R. A database and evaluation methodology for optical flow. International Journal of Computer Vision, 2011, 92(1): 1-31[26] Wang Wei-Wei, Han Yu, Feng Xiang-Chu. Image denoising based on nonlocal diffusion. Acta Optica Sinica, 2010, 30(2): 373-377(王卫卫, 韩雨, 冯象初. 基于非局部扩散的图像去噪. 光学学报, 2010, 30(2): 373-377)[27] Su Juan, Lin Xing-Gang, Liu Dai-Zhi. A multi-sensor image registration algorithm based on structure feature edges. Acta Automatica Sinica, 2009, 35(3): 251-257(苏娟, 林行刚, 刘代志. 一种基于结构特征边缘的多传感器图像配准方法. 自动化学报, 2009, 35(3): 251-257)

施引文献

资源附件(0)

访问统计