基于差分进化P系统的多模态图像配准

高志升; 张铖方; 胡占强; 耿龙

doi:10.3788/OPE.20152313.0685

您当前的位置：

首页 >

文章列表页 >

基于差分进化P系统的多模态图像配准

更新时间：2020-08-13

- 基于差分进化P系统的多模态图像配准
- Multi-modal image registration based on P system with differential evolution
- 光学精密工程 2015年23卷第10z期页码：684-694
- 作者机构：
  
  西华大学无线电管理技术研究中心, 四川成都 610039
- 作者简介：
- 基金信息：
  
  宇航动力学国家重点实验室开放基金资助项目(No.2015ADL-DW0302)();四川省教育厅重点项目(No.14ZA0118)()
- DOI：10.3788/OPE.20152313.0685
  中图分类号： TP391.4
- 收稿日期：2015-06-05，
  
  修回日期：2015-06-21，
  
  纸质出版日期：2015-11-14
- 稿件说明：
移动端阅览
高志升, 张铖方, 胡占强等. 基于差分进化P系统的多模态图像配准[J]. 光学精密工程, 2015,23(10z): 684-694

GAO Zhi-sheng, ZHANG Cheng-fang, HU Zhan-qiang etc. Multi-modal image registration based on P system with differential evolution[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 684-694
高志升, 张铖方, 胡占强等. 基于差分进化P系统的多模态图像配准[J]. 光学精密工程, 2015,23(10z): 684-694 DOI： 10.3788/OPE.20152313.0685.

GAO Zhi-sheng, ZHANG Cheng-fang, HU Zhan-qiang etc. Multi-modal image registration based on P system with differential evolution[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 684-694 DOI： 10.3788/OPE.20152313.0685.

摘要

利用膜计算的极大并行特点

提出一种在P系统框架下的多模态图像配准(DE-MCIR)算法。设计了一种细胞型P系统的膜结构

细胞膜中一个对象表示一组浮动图像变换参数。使用改进后的差分进化算法优化对象

并使用所设计的两种转运规则更新最优参数对象。最终

整个P系统的最优变换参数对象均保留在表层膜中。对卫星图像、红外与可见光等3类多模态图像进行了配准实验。结果显示:对于卫星图像配准实验

DE-MCIR的平均互信息值为1.4306

标准差为0.00341;对于红外与可见光等多模态卫星图像配准

DE-MCIR的平均互信息值为0.0402

标准差为0.00016;对于红外与可见光等多模态真实图像配准

DE-MCIR的平均互信息值为0.0125

标准差为0.00187。与基于遗传算法(GA)、粒子群优化算法(PSO)和PSO&Powell的图像配准算法相比

DE-MCIR算法显示了更好的优越性

不仅具有更好的全局寻优能力

还有更高的配准精度和更强的鲁棒性。

Abstract

A multi-modal image registration algorithm under the framework of P system was proposed by combining the parallel property of membrane computing with Differential Evolution(DE) algorithm

which was named as DE-MCIR(Differential Evolution-Multi-modal Computing Image Registration) algorithm. A cell-like P system of membrane structure was designed

and each object in membranes represented a group of transform parameters of floated images. All objects of each elementary membranes were evolved by modified DE algorithm. At the same time

the designed two exchange rules were used to update the best parameters. Finally

the global optimal object was stored in the skin membrane. The approach was tested on satellite images and infrared and visual images. For the experiment of satellite images

the average mutual information of DE-MCIR is 1.4306

and the standard deviation is 0.00341; For the experiment of multi-modal satellite images

the average mutual information of DE-MCIR is 0.0402

and the standard deviation is 0.00016; For the experiment of multi-modal real images

the average mutual information of DE-MCIR is 0.0125

and the standard deviation is 0.00187. These results reveal that DE-MCIR algorithm has better registration accuracy

global convergence

and robustness

and its performance is better than that of the Genetic Algorithm

Particle Swarm Algorithm(PSO) and PSO Powell algorithm.

关键词

Keywords

references

张婧. 基于进化算法的图像配准[D]. 上海:华东师范大学, 2014. ZHANG J. Image Registration Based on Evolutionary Algorithm[D].Shanghai:East China Normal University,2014.(in Chinese)

ROOZGARD A, BARZIQAR N, CHENG S,et al.. Medical image registration using sparse coding and belief propagation[C]. Annual International Conference of the IEEE, San Diego, CA:IEEE, 2012:1141-1144.

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):1698-1705. LIU S L, SUN G,NIU ZH D,et al.. Registration of DSM data and remote sensing image based on relative phase hisogram[J]. Opt. Precision Eng., 2014,22(6):1698-1705.(in Chinese)

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

王健博,朱明. 基于字典描述向量的实时图像配准[J]. 光学精密工程,2014,22(6):1615-1621. WANG J B,ZHU M. Real time image registration based on dictionary feature descriptor[J].Opt.Precision Eng.,2014,22(6):1615-1621.(in Chinese)

TANG K S, MAN K F, KWONG S, et al..Genetic algorithms and their applications[J].IEEE Signal Processing Magazine,1996,13(6):22-37.

BAHU B,JEHAN M M. Differential evolution for multi-objective optimization[J].Evolutionary Computation,2003,4:8-12.

杨启文,蔡亮,蔡云灿. 差分进化算法综述[J]. 模式识别与人工智能, 2008,21(4):506-513. YANG Q W, CAI L,CAI Y C,et al.. A survey of differential evolution algorithms[J]. PR&AI, 2008,21(4):506-513.(in Chinese)

CLÁUDIA O Q, EVARISTOC B Jr,JOSÉCARLOS P. The use of particle swarm optimization for dynamical analysis in chemical processes[J]. Computers&Chemical Engineering,2002,26(12):1783-1793.

李红梅.基于遗传算法的图像匹配算法研究[J]. 计算机与数字工程,2013,41(11):1823-1825. LI H M.Image matching algorithm based on genetic algorithm[J].Computer&Digital Engineering,2013,41(11):1823-1825.(in Chinese)

WACHOWIAK M P,SMOLIKOVA R,ZHENG Y F,et al.. An approach to multimodal biomedical image registration utilizing particle swarm optimization[J].IEEE Transactions on Evolutionary Computation,2004,8(3):289-301.

冯林,严亮,黄德根,等. PSO和Powell混合算法在医学图像配准中的应用研究[J]. 北京生物医学工程,2005,24(1):8-12. FENG L,YAN L,HUANG D G,et al.. A study of PSO and powell hybrid algorithm applied in medical image registration[J]. Beijing Biomedical Engineering, 2005,24(1):8-12.(in Chinese)

PĂUN G.Computing with membranes[J].Journal of Computer System Sciences, 2000,61(1):108-143.

BUSI N.Using well-structured transition systems to decide divergence for catalytic P systems[J].Theoretical Computer Science,2007,372(2-3):125-135.

PĂUN G. The Oxford Handbook of Membrane Computing[M].New York:Oxford University Press, 2010.

BERNARDINI F. Cell communication in tissue P systems:University results[J]. Soft Computing,2005,9(9):640-649.

黄亮. 膜计算优化方法研究[D]. 杭州:浙江大学, 2007. HUANG L. Research of Optimization algo rithm based on membrane computing[D]. Hangzhou:Zhejiang University, 2014.(in Chinese)

谢佩军. 一种基于膜计算的遗传算法图像分割方法[J]. 软件,2014,35(9):80-85. XIE P J. A GA-based image segmentation using membrane computing[J]. SOFTWARE, 2014,35(9):80-85.(in Chinese)

宁彬. 基于膜计算的蝙蝠算法在云计算资源调度的研究[J]. 计算机应用研究, 2015,32(3):830-833. NING B. Bats algorithm research in cloud computing resource scheduling based on membrane computing[J]. Application Research of Computers, 2015,32(3):830-833.(in Chinese)

葛平平. 膜计算优化PID控制在煤炭分拣机器人中的应用[J]. 煤炭工程, 2014,46(8):139-142. GE P P. Application of PID control on coal sorting robot system optimized with membrane computing[J]. Coal Engineering, 2014,46(8):139-142.(in Chinese)

吴亮红. 差分进化算法及应用研究[D].长沙:湖南大学,2007. WU L H. The Research and Application of Differential Evolution Algorithm[D].Changcha:Hunan University,2007.(in Chinese)

PRICE K. Differential evolution a fast and simple numerical optimizer[C]. Biennial Conference of the North American Fuzzy Information Processing Society, New York, 1996:524-527.

浏览量

137

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据