基于图像特征和光流场的非刚性图像配准

纪慧中; 贾大宇; 董恩清; 薛鹏; 唐振超

doi:doi:10.3788/ope.20172509.2469

光学精密工程, 2017, 25 (9): 2469, 网络出版: 2017-10-30

基于图像特征和光流场的非刚性图像配准

Non-rigid registrations based on image characteristics and optical flows

论文大纲

纪慧中 ^*贾大宇董恩清薛鹏唐振超

作者单位

山东大学（威海）机电与信息工程学院, 山东威海 264200

图像配准非刚性配准特征提取光流场模型圆形描述子 image registration non-rigid registration feature extraction optical-flow model circle descriptor

摘要

考虑传统非刚性图像配准方法无法同时满足配准精度和配准时间要求, 综合图像的特征和灰度信息, 提出了几种改进的非刚性图像配准方法: 基于圆形描述子特征的非刚性配准方法（Circle Descriptor Feature, CDF）, 基于动态驱动力Demons的非刚性配准方法（Dynamic Driving Force Demons, DDFD）, 和基于图像特征和光流场的非刚性配准方法。CDF方法通过提取图像的特征点, 采用圆形描述子代替传统方法的正方形描述子来保证图像的旋转不变性, 提高配准速度; DDFD方法通过引入驱动力系数动态改变驱动力, 有效地解决了传统方法配准时间和配准精度低的问题; 基于图像特征和光流场的非刚性配准方法则首先提取浮动图像和参考图像的特征点, 然后利用提取的特征点进行粗配准（特征级配准）, 再采用基于光流场的方法进行精细配准（像素级配准）, 最终实现配准精度和配准时间的兼顾。对checkboard测试图像、自然图像、脑部MR图像、肝部CT图像进行了实验测试, 结果表明, 本文方法在配准时间、配准精度及对大形变图像的适应性方面均优于传统尺度不变特征转换（ SIFT ）、加速鲁棒特征（SURF）、Demons、Active Demons和全变差正则项-L1范数项（TV-L1）等方法。

Abstract

As the non-rigid image registration methods can not meet the requirements of registration accuracy and registration time simultaneously, three kinds of improved non-rigid registration methods are proposed based on image characteristics and image gray. These non-rigid registration methods were based on the Circle Descripto increases Feature (CDF), Dynamic Driving Force Demons (DDFD) and image characteristics and optical flow, respectively. In CDF method, feature points were extracted from the images, and the circle descriptor is used in the method instead of square descriptor in classical methods, by which the rotation invariance was maintained and the speed of the registration was increased. In DDFD method, the driving force was changed by introducing the driving force coefficient, so that the registration time and registration accuracy were improved effectively. In registration methods based on image characteristics and optical flow, the feature points were extracted from a float image and a reference image by using registration method based on image characteristics, and these extracted feature points were used to get a coarse registered image (feature level registration); then the optical-flow method was used to register accurately (pixel level registration) for the coarse registered image and to achieves the purpose of taking account of the registration accuracy and registration time. The experiments on checkboard images, natural images, brain MR images and liver CT images were performed and the results show that the proposed methods are better than the classical methods such as Scale-invariant Feature Transform (SIFT), Speeded-Up Robust Features（SURF）, Demons, Active Demons and Total Variation Regularization/L1 norm (TV-L1) in registration time, registration accuracy and adaptability for large-deformation images.

参考文献

[1] BROWNL G. A Survey of image registration techniques ［J］. ACM Computing Surveys, 1992, 24(4): 325-376.

[2] PRADHANS, PATRA D. Enhanced mutual information based medical image registration ［J］. IET Image Processing, 2016, 10(5): 418-427.

[3] MISHRAB, PATI U C, SINHA U. Modified demons registration for highly deformed medical image ［C］. 2015 Third International Conference on Image Information Processing (ICIIP), IEEE, 2015: 152-156.

[4] KASHYAPM, BHATTACHARYA M. Medical image registration using extremal region based interest point ［C］. IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS), IEEE, 2015: 243-247.

[5] VETTERC, LASSER T, OKUR A, et al.. 1D-3D registration for intra-operative nuclear imaging in radio-guided Surgery ［J］. IEEE Transactions on Medical Imaging, 2015, 34(2): 608-617.

[6] GRUSLYSA, ACOSTA-CABRONERO J, NESTOR P J, et al.. A new fast accurate nonlinear medical image registration program including surface preserving regularization ［J］. IEEE Transactions on Medical Imaging, 2014, 33(11): 2118-2127.

[7] 余先川, 吕中华, 胡丹. 遥感图像配准技术综述［J］. 光学精密工程, 2013, 21(11): 2960-2972.

YU X CH, L ZH H, HU D. Review of remote sensing image registration techniques ［J］.Opt. Precision Eng., 2013, 21(11): 2960-2972. (in Chinese)

[8] 刘松林, 孙刚, 牛照东, 等. 基于相对相位直方图的数字表面模型数据与遥感图像配准［J］. 光学精密工程, 2014, 22(6): 1696-1705.

LIU S L, SUN G, NIU ZH D, et al.. Registration of DSM data and remote sensing image based on relative phase histogram ［J］.Opt. Precision Eng., 2014, 22(6): 1696-1705. (in Chinese)

[9] PAULS, PATI U C. Remote sensing optical image registration using modified uniform robust SIFT ［J］. IEEE Geoscience and Remote Sensing Letters, 2016, 13(9): 1300-1304.

[10] LOWED G. Object recognition from local scale-invariant features ［C］. Proceedings of the Seventh IEEE International Conference on Computer Vision, IEEE, 1999: 1150-1157.

[11] BAYH, ESS A, TUYTELAARS T, et al.. Speeded-up robust features (SURF) ［J］. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

[12] THIRIONJ P. Image matching as a diffusion process: an analogy with Maxwells Demons ［J］. Medical Image Analysis, 1998, 2(3): 243-260.

[13] WANGH, DONG L, ODANIEL J, et al.. Validation of an accelerated ‘demons’ algorithm for deformable image registration in radiation therapy ［J］. Physics in Medicine and Biology, 2005, 50(12): 2887-2905.

[14] TANGZ C, XUE P, YANG E, et al.. An effective non-rigid image registration method based on active demons algorithm ［C］. IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS), IEEE, 2016: 124-129.

[15] REAUNGAMORNRATS, DE SILVA T, UNERI A, et al.. MIND demons: symmetric diffeomorphic deformable registration of MR and CT for image-guided spine surgery［J］. IEEE Transactions on Medical Imaging, 2016, 35(11): 2413-2424.

[16] 薛鹏, 杨佩, 曹祝楼, 等. 基于平衡系数的Active Demons非刚性配准算法［J］. 自动化学报, 2016, 42(9): 1389-1400.

XUE P, YANG P, CAO ZH L, et al.. Active demons non-rigid registration algorithm based on balance coefficient ［J］. Acta Automatica Sinica, 2016, 42(9): 1389-1400. (in Chinese)

[17] MISHRAA, MONDAL P, BANERJEE S. VLSI-Assisted nonrigid registration using modified demons algorithm ［J］. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2015, 23(12): 2913-2921.

[18] POCKT, URSCHLER M, ZACH, et al.C. A duality based algorithm for TV-L1-optical-flow image registration ［C］. Proceedings of the 10th International Conference on Medical Image Computing and Computer-Assisted Intervention, ACM, 2007: 511-518.

[19] ZACHC, POCK T, BISCHOF H. A duality based approach for realtime TV-L1 optical flow ［M］.HAMPRECHT F A, SCHNRR C, JHNE B. Pattern Recognition. DAGM 2007. Lecture Notes in Computer Science. Berlin: Springer, 2007: 214-223.

[20] 林相波, 邱天爽, NICOLIER F, 等. Active Demons可变形图像配准算法研究［J］. 中国生物医学工程学报, 2008, 27(4): 636-640.

LIN X B, QIU T SH, NICOLIER F, et al.. The study of active demons algorithm for deformable image registration ［J］. Chinese Journal of Biomedical Engineering, 2008, 27(4): 636-640. (in Chinese)

[21] CHAMBOLLEA. An algorithm for total variation minimization and applications ［J］. Journal of Mathematical Imaging and Vision, 2004, 20(1-2): 89-97.

纪慧中, 贾大宇, 董恩清, 薛鹏, 唐振超. 基于图像特征和光流场的非刚性图像配准[J]. 光学精密工程, 2017, 25(9): 2469. JI Hui-zhong, JIA Da-yu, DONG En-qing, XUE Peng, TANG Zhen-chao. Non-rigid registrations based on image characteristics and optical flows[J]. Optics and Precision Engineering, 2017, 25(9): 2469.

基于图像特征和光流场的非刚性图像配准

关于本站 Cookie 的使用提示

全站搜索

基于图像特征和光流场的非刚性图像配准

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索