基于MAS的医学图像分割关键技术研究
|
摘要
在临床诊断和病理学研究中,为了准确地分辨医学图像中的正常组织结构和异常病变,需要对医学图像进行分割。由于医学图像对比度较低,加之组织特征的可变性、不同组织之间或者组织和病灶之间边界的模糊性以及微细结构(如血管、神经)分布的复杂性,使得医学图像分割成为一个难点。
论文在分析了国内外有关医学图像分割方法相关文献的基础上,基于Agent原理与技术,提出了一种新的基于MAS(Multi-Agent System)的医学图像分割方法。论文的主要工作及创新点是:
(1)对国内外典型医学图像分割方法进行了深入地分析,综述了图像分割的基本方法,并针对医学图像的特点,阐述了基于MAS的医学图像分割方法的可行性和必要性。
(2)对MAS协作求解机制和Agent群体强化学习进行了详细介绍。讨论了几种典型的MAS体系结构,指出MAS不仅在结构上存在相关性,而且在行为上也存在相关性,这些相关性正是MAS协作的起因。将传统的强化学习技术引入到MAS中,形成Agent群体强化学习机制。
(3)在上述工作基础上,通过对典型MAS组织结构优缺点的分析,提出一个基于Agent图(Agent Graph)的三级MAS协作组织模型,该模型较好地兼顾了系统对通信开销、效率、可靠性等方面的要求。以个体强化学习和Agent组(Agent Team)的概念为基础,设计了一种引入先验知识的强化函数,提出了基于Agent组的群体强化学习算法。
(4)针对医学图像分割,提出一种图像分割的高层模型,对该模型的各个部分进行了详细介绍,指出了模型设计中的几个关键问题。根据该模型,给出了基于MAS的医学图像分割技术的流程和关键算法。
(5)利用论文的分割算法对图像进行了分割实验,人脑模拟图像组织的分割和FCM方法的分割视觉效果对比,人脑冠状面MR图像的MAS分割和ML分割及CGS分割的比较以及异常脑组织的分割实验结果表明,论文的基于MAS的自适应分割算法较好地完成了图像的分割,视觉效果良好,具有很好的适应性,分割效果与领域专家的意见基本一致,在医学应用上具有实际意义。
(6)基于集对分析SPA(Set Pair Analysis),给出了分割方法评价模型,并用该方法对论文的实验工作进行了初步的分析比较。
It is required to segment the medical images in order to distinguish normal tissues and abnormal pathological changes in the clinic diagnose and pathology research. As the usually lower contrast of medical image, the changes of tissue character, the fuzzy character of different tissue or between tissue and focus and the distributing complexity of imperceptibility structure, such as vas and nerve, the medical image segmentation becomes a difficult problem.
After a detailed investigation about the development of medical image segmentation in domestic and foreign related fields, the paper brings forward a new method of medical image adaptive segmentation based on MAS (Multi-Agent System). Its main contents and innovations include:
(1) This paper provides an elaborately analysis about typical medical image segmentation methods of domestic and foreign related fields, shows a more comprehensive overview of the image segmentation technology. The feasibility and necessity of medical image segmentation based on MAS was expounded.
(2) This paper carries out a detailed introduction of the mechanisms of MAS collaboration and the reinforcement learning of Agent groups. After the discussion of several typical MAS architecture, this paper points out the MAS collaboration is aroused by the relevance which existing in the structure and behavior of MAS. The introduction of traditional reinforcement learning techniques into MAS forms the Agent group reinforcement learning mechanism.
(3) Based on the above works, a three-tier MAS collaboration organization model was proposed based on Agent graph after an analysis of the advantages and disadvantages of the typical MAS organizational structure. The model has better balance between the communication costs, efficiency, reliability, and so on. Using the individual reinforcement learning and the concept of Agent team, this paper designs a reinforcement function which introduced to priori knowledge, brings forward a group reinforcement learning algorithm based on Agent group.
(4) For the purposes of medical image segmentation, the paper gives a high-level modal of image segmentation and a detailed introduction about the model, and points out several key issues in the design process. According to the model, we give the flow and key algorithm of the image segmentation technology.
(5) Image segmentation experiments were conducted using our algorithm. The vision effect contrast of different tissues of brain simulation image by MAS and FCM techniques, the human brain coronal MR image segmentation by MAS, ML and CGS segmentation and the abnormal brain tissue segmentation experimental validate this method is effective to realize the segmentation. The result of experiment indicates the method can implement the automatic segmentation and its vision effect is excellent with good adaptability. The segmentation effect is basically consistent with the expert of medical image segmentation field and significative in medical applications.
(6) This paper presented a succinct segmentation technology evaluation model which based on Set Pair Analysis. Our experimental results were analyzed and compared using this method.
论文在分析了国内外有关医学图像分割方法相关文献的基础上,基于Agent原理与技术,提出了一种新的基于MAS(Multi-Agent System)的医学图像分割方法。论文的主要工作及创新点是:
(1)对国内外典型医学图像分割方法进行了深入地分析,综述了图像分割的基本方法,并针对医学图像的特点,阐述了基于MAS的医学图像分割方法的可行性和必要性。
(2)对MAS协作求解机制和Agent群体强化学习进行了详细介绍。讨论了几种典型的MAS体系结构,指出MAS不仅在结构上存在相关性,而且在行为上也存在相关性,这些相关性正是MAS协作的起因。将传统的强化学习技术引入到MAS中,形成Agent群体强化学习机制。
(3)在上述工作基础上,通过对典型MAS组织结构优缺点的分析,提出一个基于Agent图(Agent Graph)的三级MAS协作组织模型,该模型较好地兼顾了系统对通信开销、效率、可靠性等方面的要求。以个体强化学习和Agent组(Agent Team)的概念为基础,设计了一种引入先验知识的强化函数,提出了基于Agent组的群体强化学习算法。
(4)针对医学图像分割,提出一种图像分割的高层模型,对该模型的各个部分进行了详细介绍,指出了模型设计中的几个关键问题。根据该模型,给出了基于MAS的医学图像分割技术的流程和关键算法。
(5)利用论文的分割算法对图像进行了分割实验,人脑模拟图像组织的分割和FCM方法的分割视觉效果对比,人脑冠状面MR图像的MAS分割和ML分割及CGS分割的比较以及异常脑组织的分割实验结果表明,论文的基于MAS的自适应分割算法较好地完成了图像的分割,视觉效果良好,具有很好的适应性,分割效果与领域专家的意见基本一致,在医学应用上具有实际意义。
(6)基于集对分析SPA(Set Pair Analysis),给出了分割方法评价模型,并用该方法对论文的实验工作进行了初步的分析比较。
It is required to segment the medical images in order to distinguish normal tissues and abnormal pathological changes in the clinic diagnose and pathology research. As the usually lower contrast of medical image, the changes of tissue character, the fuzzy character of different tissue or between tissue and focus and the distributing complexity of imperceptibility structure, such as vas and nerve, the medical image segmentation becomes a difficult problem.
After a detailed investigation about the development of medical image segmentation in domestic and foreign related fields, the paper brings forward a new method of medical image adaptive segmentation based on MAS (Multi-Agent System). Its main contents and innovations include:
(1) This paper provides an elaborately analysis about typical medical image segmentation methods of domestic and foreign related fields, shows a more comprehensive overview of the image segmentation technology. The feasibility and necessity of medical image segmentation based on MAS was expounded.
(2) This paper carries out a detailed introduction of the mechanisms of MAS collaboration and the reinforcement learning of Agent groups. After the discussion of several typical MAS architecture, this paper points out the MAS collaboration is aroused by the relevance which existing in the structure and behavior of MAS. The introduction of traditional reinforcement learning techniques into MAS forms the Agent group reinforcement learning mechanism.
(3) Based on the above works, a three-tier MAS collaboration organization model was proposed based on Agent graph after an analysis of the advantages and disadvantages of the typical MAS organizational structure. The model has better balance between the communication costs, efficiency, reliability, and so on. Using the individual reinforcement learning and the concept of Agent team, this paper designs a reinforcement function which introduced to priori knowledge, brings forward a group reinforcement learning algorithm based on Agent group.
(4) For the purposes of medical image segmentation, the paper gives a high-level modal of image segmentation and a detailed introduction about the model, and points out several key issues in the design process. According to the model, we give the flow and key algorithm of the image segmentation technology.
(5) Image segmentation experiments were conducted using our algorithm. The vision effect contrast of different tissues of brain simulation image by MAS and FCM techniques, the human brain coronal MR image segmentation by MAS, ML and CGS segmentation and the abnormal brain tissue segmentation experimental validate this method is effective to realize the segmentation. The result of experiment indicates the method can implement the automatic segmentation and its vision effect is excellent with good adaptability. The segmentation effect is basically consistent with the expert of medical image segmentation field and significative in medical applications.
(6) This paper presented a succinct segmentation technology evaluation model which based on Set Pair Analysis. Our experimental results were analyzed and compared using this method.
引文
[1]朱峰.医学图像自动分割若干关键技术研究[D].江苏:江苏大学.2006,03.
[2]张毓晋.图像分割[M].北京:清华大学出版社,2000.
[3]毛心军.面向主体的软件开发[M].北京:清华大学出版社.2005.
[4]陈小波.基于自适应多Agent的图像分割[D].江苏:江苏大学2007,05.
[5]韩兰君.基于M_AS的医学图像分割算法的研究[D].江苏:江苏大学2006,12.
[6]Gonzalez R C,Woods R E.Digital Image Processing[M].3rd.ed.Addison-Wesley.1992.
[7]Zhang Y J.Quantitative image quality measure and their application in segmentation evaluation[J].Journal of Electronics.1997,14:97-103.
[8]谢凤英,姜志国.基于最大方差的免疫细胞图像双阈值分割[J].中国体视学与图像分析,2007,Vol.12,N1.,59-61.
[9]Roberts I G.Machine Perception of Three Dimensional Solid[J].Optical and Electro-Optical Information Processing.Tipper J,et al.,eds.,1965,159-197.
[10]曹婧华,冉彦忠,刘沛先.Canny算法在细胞图像边缘检测中的应用[J].中国医学装备,2007,Vol.14,No.1,36-37.
[11]Kass M,Witldn A,Terzopouls D.Snake:active contour models[J].Proceeding of International Journal of Computer Vision,1988.321-331.
[12]Xu C Y,Jerry J L.Snakes,shape,and gradien vector flow[J].IEEE Trans,Image Processing,1998,7(3):359-369.
[13]Zeyun Yu,Chandrajit Bajaj.Image segmentation using gradient vector diffusion and region merging[C].Quebec,Canada:Proceedings of the 16th International Conference on Pattern Recognition,2002.941-944.
[14]尤建洁,周则明等.基于模拟退火的简化Snake弱边界医学图像分割[J].中国图象图形学报,2004,1006-8961.
[15]BAILLARD C,HELLIER P,BARILLOT C.Segmentation of brain 3D MR images using level sets and dense registration[J].Medical Image Analysis,2001,5(3):185-194.
[16]ZHU S C,MUMFORD D.Gibbs reaction and diffusion equations[A].Proc.6th Int'l Conf.On Computer Vision[C].India:Bambay,1998.847-856.
[17]赵志峰,张尤赛.医学图像分割综述[J].华东船舶工业学院学报,2003,17(3)43-48.
[18]罗宏文,马驷良,徐中宇.基于水平集方法的显微细胞图像分割[J].吉林大学学报(理学版).Vol.44,No.5,2006.760-763.
[19]ASARI K V.Training of a feed-forward multiple-valued neural network by error back-propagation with a multi level threshold function[J].IEEE Transactionson Neural Networks,2001,12(6):1519-1521.
[20]CHENG K S,LIN J S,MAO C W.The application of competitive hopfield neuralnet work to medical image segmentation[J].IEEE T Med Imaging,1996,15(4):560-567.
[21]BAO X,XIAO S,XU Z.Three-dimensional segmentation of CT images using neural network[J].Proceedings of the 20th Annual International Conference of IEEE Engineering in Medicine and Biology Society,1998,20(2):605-608.
[22]AHMED M N,FARAG A A.Two-stage neural network for volume segmentation of medical images[J].Proceedings of IEEE International Conference On Neural Networks,1997(3):1373-1377.
[23]KOBASHI S,KAMIURA N,HATA Y,etal.Fuzzy information granulation on blood vessel extraction from3-D TO FMRA image[J].International Journal of Pattern Recognition and Artificial Intelligence,2000,14(4):409-425.
[24]PHAM D L,PRINCE J L.An adaptive fuzzy C2 means algorithm for image segmentation in the presence of intensity in homogeneities[J].Pattern Recognition,1999,20(1):57-68.
[25]叶秀清,顾伟康.快速模糊分割算法[J].模式识别与人工智能,1996,9(1):66-70.
[26]耿伯英,杨静宇.基于多分辨率分析及QFCM算法的图像分割方法研究[J],计算机研究与发展,2000,37(8):948-953.
[27]聂生东,陈瑛,顾顺德,等.磁共振颅脑图像快速模糊聚类分割算法的研究[J].中国生物医学工程学报,2001,20(2):104-109.
[28]马峰,唐泽圣.多尺度几何活动曲线及MR图像边界提取[J].计算机学报,2000,23(8):829-834.
[29]陈武凡.小波分析及其在图像处理中的应用[M].北京:科学出版社,2002.
[30]樊尚春,周游.医学图像处理技术概述.中国科技论文在线http://www.paper.edu.cn
[31]M.Minsky.The Society of Mind.Simon and Schuster[M],New York.1985.
[32]Wooldridge M J,Jennings N R.Agent theories,architectures,and languages:A survey in agents[A].Lecture Notes in Artificial Intelligence[C].Amsterdam:Springer Verlay,1994.890:1-32.
[33]Cohen P,Levesque H.Confirmations and Joint action[C].IJCAI,Proceedings of the Internationgal Joint Conference on Artificial Intelligence,1991,(2):951-957.
[34]Nicholas R,Jennings.A Roadmap of Agent Research and Development[J].Autonomou Agents and Multi-Agent System.1998,1:7-28.
[35]Nicholas R,Jennings.Commitments and Conventiongs:The Foundation of Coordination in Multi-Agent System[J].The Knowledge Engineering Review,1993,8(3):223-250.
[36]Grosz B.Collaborative System[J].AI Magazine,1995.17(2):67-85.
[37]Maes P.Learning Behavior Networks from Experience[C].In Varela,F.and Bourgine,P.In Proceeding of the First European Conference on Artificial Life,48-57,MIT-Press,Paris.
[38]Luo Y,Liu K,Davis D N.A multi-agent decision support system for stock trading[J].IEEE Network,2003,160):20-27.
[39]程显毅.Agent计算[M].哈尔滨:黑龙江科学技术出版社.2003.
[40]H.Kitano,M.Tambe,P.Stone,et al.The RoboCup Synthetic Agent Challenge 97[J].San Francisco,CA:Morgan Kaufmann,1997,24-29.
[41]Bradshaw,J.M.An Introduction to Software Agents[A].In:Software Agents,J.M.Bradshaw(Ed.),Menlo Park Calif,AAAI Press,1997,pages 3-46.
[42]高阳,陈世福.强化学习研究综述[J].自动化学报.2004,30(1)86-100.
[43]Fox M S.An Organizational View of Distributed Systems[J].IEEE trans.1981,SMC,SMC-11(1):70-80.
[44]谢希仁.计算机网络[M].北京:电子工业出版社,1999.
[45]Bell,P.R.,et al.Review of Point-to-Point Network Routing Algorithms[J].IEEE Commun.Magazine,vol.24,No.1,34-38,Jan.1986.
[46]M J Matalic.Reward Functions for Accelerated Learning[C].In:Proc Int Confon Machine Learning,1994,181-189.
[47]Kousuke Inoue,Jun OTA,Tomohiko,Katayama et al.Acceleration of Reinforcement Learning by A Mobile Robot Using Generalized Rules[C].In:Proc IEEE int Conf Intelligent Robots and Systems,2000,885-890.
[48]L P Kaelbling.Learning in Embedded Systems[D].Ph.D thesis Standford University,1990.
[49]罗青,李智军,吕恬生.复杂环境中的多智能体学习[J].上海交通大学学报.2002,3:302-305.
[50]程显毅,李淑琴,夏德深.基于主智能体的群体学习算法GLBMA[J].江苏大学学报(自然科学版).2005,Vol.26,No.5,437-439.
[51]Jiming Liu.多智能体原理与技术.北京:清华大学出版社,2003.
[52]Edouard Duchesnay,Jean-Jacques Montois,Yann Jacquelet.Cooperative agents society organized as an irregular pyramid:A mammography segmentation application[J].Pattern Recognition letters 2003(24),2435-2445.
[53]Alain Boucher,Catherine.A Multi-Agent System to Segment Living Cells[J].Proceeding of ICPR,1996,558-562.
[54]罗述谦,周果宏.医学图像处理与分析[M].北京:科学出版社,2003.
[55]印鉴.基于演化Agent的图像特征提取方法[J].小型微型计算机系统.Vol.24,No.12,2003.2181-2184.
[56]Haralick R M.Performance characterization in computer vision[C].CVGIP-IU,1994,60:245-249.
[57]Zhang Y J,Gerbrands J J.Objective and quantitative segmentation evaluation and comparision[J].Signal Processing,1994,39:43-45.
[58]Zhang Y J.Comparision of segmentation evaluation criteria[C].Proceedings of 2ICSP,1993,870-873.
[59]Gerbrands J J.Segmentation of noisy image[M].Delft University of Technology,The Netherlands,1988.
[60]Leung C K,Lam F K.Performance analysis for a class of iterative image thresholding algorithms[J].Pattern Recognition,1996,29(9):1523-1530.
[61]Nazif A M,Levine M D.Low level image segmentation:an expert system[C].IEEE-PAMI,1984,6:555-577.
[62]Levine M D,Nazif A M.Dynamic measure of computer generated image segmentation[C].IEEE-PAMI,1985,7:155-164.
[63]Brink A D.Gray-level thresholding of images using a correlation criterion[J].Pattern Recognition Letters,1989,9:335-341.
[64]Cseke I,Fazekas Z.Comments on gray-level thresholding of image using a correlation criteria[J].Pattern Recognition Letters,1990,11:209-65]
[65]Otsu N.A threshold selection method from gray-level histogram[J].IEEE-SMC,1979,9:62-66.
[66]Sahoo P K,et al.A survey ofthresholding techniques[C].CVGIP,1988,41:233-260.
[67]赵克勤.集对分析及其初步应用[M].杭州:浙江科技出版社,2000.
[68]高波,袁洪林.资产评估参照物选择的同异反集对分析法[J].计算机工程与应用.2002,38(增刊):32-36.
[2]张毓晋.图像分割[M].北京:清华大学出版社,2000.
[3]毛心军.面向主体的软件开发[M].北京:清华大学出版社.2005.
[4]陈小波.基于自适应多Agent的图像分割[D].江苏:江苏大学2007,05.
[5]韩兰君.基于M_AS的医学图像分割算法的研究[D].江苏:江苏大学2006,12.
[6]Gonzalez R C,Woods R E.Digital Image Processing[M].3rd.ed.Addison-Wesley.1992.
[7]Zhang Y J.Quantitative image quality measure and their application in segmentation evaluation[J].Journal of Electronics.1997,14:97-103.
[8]谢凤英,姜志国.基于最大方差的免疫细胞图像双阈值分割[J].中国体视学与图像分析,2007,Vol.12,N1.,59-61.
[9]Roberts I G.Machine Perception of Three Dimensional Solid[J].Optical and Electro-Optical Information Processing.Tipper J,et al.,eds.,1965,159-197.
[10]曹婧华,冉彦忠,刘沛先.Canny算法在细胞图像边缘检测中的应用[J].中国医学装备,2007,Vol.14,No.1,36-37.
[11]Kass M,Witldn A,Terzopouls D.Snake:active contour models[J].Proceeding of International Journal of Computer Vision,1988.321-331.
[12]Xu C Y,Jerry J L.Snakes,shape,and gradien vector flow[J].IEEE Trans,Image Processing,1998,7(3):359-369.
[13]Zeyun Yu,Chandrajit Bajaj.Image segmentation using gradient vector diffusion and region merging[C].Quebec,Canada:Proceedings of the 16th International Conference on Pattern Recognition,2002.941-944.
[14]尤建洁,周则明等.基于模拟退火的简化Snake弱边界医学图像分割[J].中国图象图形学报,2004,1006-8961.
[15]BAILLARD C,HELLIER P,BARILLOT C.Segmentation of brain 3D MR images using level sets and dense registration[J].Medical Image Analysis,2001,5(3):185-194.
[16]ZHU S C,MUMFORD D.Gibbs reaction and diffusion equations[A].Proc.6th Int'l Conf.On Computer Vision[C].India:Bambay,1998.847-856.
[17]赵志峰,张尤赛.医学图像分割综述[J].华东船舶工业学院学报,2003,17(3)43-48.
[18]罗宏文,马驷良,徐中宇.基于水平集方法的显微细胞图像分割[J].吉林大学学报(理学版).Vol.44,No.5,2006.760-763.
[19]ASARI K V.Training of a feed-forward multiple-valued neural network by error back-propagation with a multi level threshold function[J].IEEE Transactionson Neural Networks,2001,12(6):1519-1521.
[20]CHENG K S,LIN J S,MAO C W.The application of competitive hopfield neuralnet work to medical image segmentation[J].IEEE T Med Imaging,1996,15(4):560-567.
[21]BAO X,XIAO S,XU Z.Three-dimensional segmentation of CT images using neural network[J].Proceedings of the 20th Annual International Conference of IEEE Engineering in Medicine and Biology Society,1998,20(2):605-608.
[22]AHMED M N,FARAG A A.Two-stage neural network for volume segmentation of medical images[J].Proceedings of IEEE International Conference On Neural Networks,1997(3):1373-1377.
[23]KOBASHI S,KAMIURA N,HATA Y,etal.Fuzzy information granulation on blood vessel extraction from3-D TO FMRA image[J].International Journal of Pattern Recognition and Artificial Intelligence,2000,14(4):409-425.
[24]PHAM D L,PRINCE J L.An adaptive fuzzy C2 means algorithm for image segmentation in the presence of intensity in homogeneities[J].Pattern Recognition,1999,20(1):57-68.
[25]叶秀清,顾伟康.快速模糊分割算法[J].模式识别与人工智能,1996,9(1):66-70.
[26]耿伯英,杨静宇.基于多分辨率分析及QFCM算法的图像分割方法研究[J],计算机研究与发展,2000,37(8):948-953.
[27]聂生东,陈瑛,顾顺德,等.磁共振颅脑图像快速模糊聚类分割算法的研究[J].中国生物医学工程学报,2001,20(2):104-109.
[28]马峰,唐泽圣.多尺度几何活动曲线及MR图像边界提取[J].计算机学报,2000,23(8):829-834.
[29]陈武凡.小波分析及其在图像处理中的应用[M].北京:科学出版社,2002.
[30]樊尚春,周游.医学图像处理技术概述.中国科技论文在线http://www.paper.edu.cn
[31]M.Minsky.The Society of Mind.Simon and Schuster[M],New York.1985.
[32]Wooldridge M J,Jennings N R.Agent theories,architectures,and languages:A survey in agents[A].Lecture Notes in Artificial Intelligence[C].Amsterdam:Springer Verlay,1994.890:1-32.
[33]Cohen P,Levesque H.Confirmations and Joint action[C].IJCAI,Proceedings of the Internationgal Joint Conference on Artificial Intelligence,1991,(2):951-957.
[34]Nicholas R,Jennings.A Roadmap of Agent Research and Development[J].Autonomou Agents and Multi-Agent System.1998,1:7-28.
[35]Nicholas R,Jennings.Commitments and Conventiongs:The Foundation of Coordination in Multi-Agent System[J].The Knowledge Engineering Review,1993,8(3):223-250.
[36]Grosz B.Collaborative System[J].AI Magazine,1995.17(2):67-85.
[37]Maes P.Learning Behavior Networks from Experience[C].In Varela,F.and Bourgine,P.In Proceeding of the First European Conference on Artificial Life,48-57,MIT-Press,Paris.
[38]Luo Y,Liu K,Davis D N.A multi-agent decision support system for stock trading[J].IEEE Network,2003,160):20-27.
[39]程显毅.Agent计算[M].哈尔滨:黑龙江科学技术出版社.2003.
[40]H.Kitano,M.Tambe,P.Stone,et al.The RoboCup Synthetic Agent Challenge 97[J].San Francisco,CA:Morgan Kaufmann,1997,24-29.
[41]Bradshaw,J.M.An Introduction to Software Agents[A].In:Software Agents,J.M.Bradshaw(Ed.),Menlo Park Calif,AAAI Press,1997,pages 3-46.
[42]高阳,陈世福.强化学习研究综述[J].自动化学报.2004,30(1)86-100.
[43]Fox M S.An Organizational View of Distributed Systems[J].IEEE trans.1981,SMC,SMC-11(1):70-80.
[44]谢希仁.计算机网络[M].北京:电子工业出版社,1999.
[45]Bell,P.R.,et al.Review of Point-to-Point Network Routing Algorithms[J].IEEE Commun.Magazine,vol.24,No.1,34-38,Jan.1986.
[46]M J Matalic.Reward Functions for Accelerated Learning[C].In:Proc Int Confon Machine Learning,1994,181-189.
[47]Kousuke Inoue,Jun OTA,Tomohiko,Katayama et al.Acceleration of Reinforcement Learning by A Mobile Robot Using Generalized Rules[C].In:Proc IEEE int Conf Intelligent Robots and Systems,2000,885-890.
[48]L P Kaelbling.Learning in Embedded Systems[D].Ph.D thesis Standford University,1990.
[49]罗青,李智军,吕恬生.复杂环境中的多智能体学习[J].上海交通大学学报.2002,3:302-305.
[50]程显毅,李淑琴,夏德深.基于主智能体的群体学习算法GLBMA[J].江苏大学学报(自然科学版).2005,Vol.26,No.5,437-439.
[51]Jiming Liu.多智能体原理与技术.北京:清华大学出版社,2003.
[52]Edouard Duchesnay,Jean-Jacques Montois,Yann Jacquelet.Cooperative agents society organized as an irregular pyramid:A mammography segmentation application[J].Pattern Recognition letters 2003(24),2435-2445.
[53]Alain Boucher,Catherine.A Multi-Agent System to Segment Living Cells[J].Proceeding of ICPR,1996,558-562.
[54]罗述谦,周果宏.医学图像处理与分析[M].北京:科学出版社,2003.
[55]印鉴.基于演化Agent的图像特征提取方法[J].小型微型计算机系统.Vol.24,No.12,2003.2181-2184.
[56]Haralick R M.Performance characterization in computer vision[C].CVGIP-IU,1994,60:245-249.
[57]Zhang Y J,Gerbrands J J.Objective and quantitative segmentation evaluation and comparision[J].Signal Processing,1994,39:43-45.
[58]Zhang Y J.Comparision of segmentation evaluation criteria[C].Proceedings of 2ICSP,1993,870-873.
[59]Gerbrands J J.Segmentation of noisy image[M].Delft University of Technology,The Netherlands,1988.
[60]Leung C K,Lam F K.Performance analysis for a class of iterative image thresholding algorithms[J].Pattern Recognition,1996,29(9):1523-1530.
[61]Nazif A M,Levine M D.Low level image segmentation:an expert system[C].IEEE-PAMI,1984,6:555-577.
[62]Levine M D,Nazif A M.Dynamic measure of computer generated image segmentation[C].IEEE-PAMI,1985,7:155-164.
[63]Brink A D.Gray-level thresholding of images using a correlation criterion[J].Pattern Recognition Letters,1989,9:335-341.
[64]Cseke I,Fazekas Z.Comments on gray-level thresholding of image using a correlation criteria[J].Pattern Recognition Letters,1990,11:209-65]
[65]Otsu N.A threshold selection method from gray-level histogram[J].IEEE-SMC,1979,9:62-66.
[66]Sahoo P K,et al.A survey ofthresholding techniques[C].CVGIP,1988,41:233-260.
[67]赵克勤.集对分析及其初步应用[M].杭州:浙江科技出版社,2000.
[68]高波,袁洪林.资产评估参照物选择的同异反集对分析法[J].计算机工程与应用.2002,38(增刊):32-36.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |