基于改进遗传算法的图像分割
|
摘要
遗传算法作为一种求解问题的高效并行的全局搜索方法，以其固有的鲁棒性、并行性和自适应性，使之非常适于大规模搜索空间的寻优，已广泛应用许多学科及工程领域。在计算机视觉领域中的应用也正日益受到重视，为图像分割问题提供了新而有效的方法。
本论文对图像分割算法进行了研究与比较；对遗传算法理论、遗传算法在图像分割领域的应用现状及遗传分割算法的原理、过程、结果等几方面做了研究。
通过对遗传算法运行机理的深入研究，针对一些有噪声的图像，本文提出一种基于改进遗传算法的图像分割方法。算法中采用二维编码机制；为保持种群的多样性，随机均匀地产生初始种群；遗传操作中的交叉操作中引入了一项规则防止种群退化；为使遗传算法保持种群的多样性，以防止出现未成熟收敛，本文设计了一个自适应变异算子；以及在种群更新机制方面，提出了新的解决方案。
实验结果表明，本文提出的基于改进的遗传算法优化了图像的分割，运算速度明显比传统分割算法快，而且取得了比传统算法更好的分割质量。
本文程序采用VC++6.0在WinXP 环境下编译完成。
Genetic algorithm (GA) is a sort of efficient， paralled ，full search method with its inherent virtues of robustness， parallel and self-adaptive characters. It is suitable for searching the optimization result in the large search space. Now it has been applied widely and perfectly in many study fields and engineering areas. In computer vision field GA is increasingly attached more importance. It provides the image segmentation a new and effective method.
Algorithms and analyses about image segmentation are presented .An overview on the theories and the recent development is given. Also the status of GA applied in the image segmentation field is presented， and the theories， steps， results and analyses of several GA applied in the image segmentation are given.
Through the deep research and compare on the GA fields， an improved genetic algorithm in image segmentation is proposed to effectively accomplish analysis tasks for noisy images. In the new algorithms: coding with 2-dimention chromosome is adopted; initialization of population with stochastic and symmetrical methods is produced to keep the variety of the population; A new rule is imported in the crossover operation to avoid the population degenerating; A adaptive mutation operator is proposed in the mutation operation to avoid the immature convergence; A new method is designed in the forming of the new population.
The result of experiment shows that the new algorithm can improve greatly the speed and get the better quality than the traditional algorithm.
Programs were all compiled in the Windows XP by VC++6.0.
本论文对图像分割算法进行了研究与比较；对遗传算法理论、遗传算法在图像分割领域的应用现状及遗传分割算法的原理、过程、结果等几方面做了研究。
通过对遗传算法运行机理的深入研究，针对一些有噪声的图像，本文提出一种基于改进遗传算法的图像分割方法。算法中采用二维编码机制；为保持种群的多样性，随机均匀地产生初始种群；遗传操作中的交叉操作中引入了一项规则防止种群退化；为使遗传算法保持种群的多样性，以防止出现未成熟收敛，本文设计了一个自适应变异算子；以及在种群更新机制方面，提出了新的解决方案。
实验结果表明，本文提出的基于改进的遗传算法优化了图像的分割，运算速度明显比传统分割算法快，而且取得了比传统算法更好的分割质量。
本文程序采用VC++6.0在WinXP 环境下编译完成。
Genetic algorithm (GA) is a sort of efficient， paralled ，full search method with its inherent virtues of robustness， parallel and self-adaptive characters. It is suitable for searching the optimization result in the large search space. Now it has been applied widely and perfectly in many study fields and engineering areas. In computer vision field GA is increasingly attached more importance. It provides the image segmentation a new and effective method.
Algorithms and analyses about image segmentation are presented .An overview on the theories and the recent development is given. Also the status of GA applied in the image segmentation field is presented， and the theories， steps， results and analyses of several GA applied in the image segmentation are given.
Through the deep research and compare on the GA fields， an improved genetic algorithm in image segmentation is proposed to effectively accomplish analysis tasks for noisy images. In the new algorithms: coding with 2-dimention chromosome is adopted; initialization of population with stochastic and symmetrical methods is produced to keep the variety of the population; A new rule is imported in the crossover operation to avoid the population degenerating; A adaptive mutation operator is proposed in the mutation operation to avoid the immature convergence; A new method is designed in the forming of the new population.
The result of experiment shows that the new algorithm can improve greatly the speed and get the better quality than the traditional algorithm.
Programs were all compiled in the Windows XP by VC++6.0.
引文
[1] Lee S U,Chung S Y, A comparative performance study of several global thresholding techniques for segmentation.Computer Vision, Graphics and Image Processing, 1990,52:171—190
[2]王小平,曹立明. 《遗传算法—理论、应用与软件实现》.西安交通大学出版社. 2002
[3]沈庭芝,王蕾,周长志.遗传算法在小目标图像分割中的应用.系统工程与电子技术. 2002,24(12) :86～88
[4]吴成柯,刘靖,侯格贤. 图像分割的多参量遗传算法.自动化学报. 1998.3：410～413
[5]种劲松,周孝宽,王宏琦.基于遗传算法的最佳熵阈值图像分割法. 北京航空航天大学学报. 1999.6:747～750
[6]韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术 .2002.6:91～94
[7]金聪,彭嘉雄. 利用遗传算法实现数字图像分割.小型微型计算机系统. 2002.7:875～877
[8]梁光明,刘东华,李波,唐朝京.自适应阈值分割算法的改进.自动化技术与应用.第21卷第五期:43～46
[9]陈果,左洪福.图像分割的二维最大熵遗传算法.计算机辅助设计与图形学学报.2002.6:530～534
[10]贾永红. 《计算机图像处理与分析》. 武汉大学出版社. 2001
[11]耿茵茵,蔡安妮,孙景鳌. 自动图像阈值分割算法. 计算机工程与应用. 2002.17:119～122
[12]常青,王立,邢超,王红梅,李言俊. 基于遗传算法的图像阈值选取. 计算机工程与应用. 2002.22:35～37
[13]Bhandarker S M. Image Segmentation Using Evolutionary Computation. IEEE Transactions of Evolutionary Computation, 1999,3(1):1-21
[14]Kenneth R Castle. Digital Image Processing. Prentice
Hall,1995
[15]KapurJN,SahooPK,WongAKC.Anewmethodforgray-levelpicturethresholdingusingtheentropyofthehis-togram[J].ComputerVision,GraphicsandImageProcess-ing,1985(29):273～285
[16]Wang Lei,Shen Ting-Zhi, Two-Dimensional Entropy Method Based on Genetic Algorithm, Journal of Beijing Institute of Techonlogy, 2002,Vol .11,No.2
[17]章毓晋. 《图像工程(上册)图像处理和分析》.北京.清华大学出版社.1999
[18]杨淑莹. 《VC++图像处理程序设计》. 清华大学出版社. 2003
[18]陈国良等.遗传算法及其应用.人民邮电出版社,1996
[19]王培珍,杜培明,陈维南.一种用于多阈值图像自动分割的混合遗传算法[Ｊ].中国图像图形学报,2000,5(1)
[20]PunT.Anewmethodforgray-levelpicturethresholdingus-ingtheentropyofhistogram[J].SignalProcessing,1980(2):223～237
[21]JohannsenG,BileJ.Athresholdselectionmethodusingin-formationmeasures[A].In:Proceedingsofthe6thICPR,1982.140～143
[22]汪祖媛,庄镇泉,汪炳权. 红外热图像分割中的二维灰度直方图小波变换方法[Ｊ] 红外技术,2000,22(4):1～3
[23]詹劲峰,戚劲峰,王海龙. 基于时空马尔可夫随机场的运动目标分割技术[Ｊ] 通信学报,2000,21(11):63～68
[24]景晓军,蔡安妮,孙景鳌.一种基于二维最大类间方差的图像分割方法.通讯学报,2001,4:71～76
[25]刘健庄,栗文清.灰度图像的二维Ｏｓｔｕ自动阈值分割法.自动化学报,1993,19(1):101～105
[26]Brink A D. Thresholding digital images using two dimensional entropics. Pattern Recognition,1992,25(8):803～808
[27]王培珍,陈维南.基于二维阈值化与FCM相结合的图像快速分割方法.中国图形图像学报,1998,3(9):734～738
[28]Jincong.Improvegeneticalgorithmandanalysisofitsproperty〔J〕.Mini-MicroSystems,200021(9):950～952(金聪.改进型遗传算法及其性能分析〔J〕.小型微型计算机系统.2000.21(9):950～952)
[29]薛景浩,章毓晋,林行刚.二维遗传算法用于图像动态分割.自动化
学报,2000；26（5）：749-753
[30]赵荣春,迟耀斌,朱重光.图像分割技术进展.第九届全国图像图形学学术会议论文集,中国图像图形学会,1998:547～558
[31]罗希平,田捷,诸葛婴等.图像分割方法综述.模式识别与人工智能,1999,12(3):300～312
[32]李立源,龚坚,陈维南.基于二维灰度直方图最佳一维投影的图像分割方法[J].自动化学报,1996,22(3):315～322
[33]张毅军,吴雪青,夏良正.二维熵图像阈值分割的快速递推算法[J].模式识别与人工智能,1997,10(3):259～264
[34]夏良正.数字图像处理[M].南京:东南大学出版社,1999.223～228
[35]AbutalebAS.Automaticthresholdingofgray-levelpicturesusingtwo-dimensionentropy[J].ComputerVision,Graph-icsandImageProcessing,1989(47):22～32
[36]WongAKC,SahooPK.Agray-levelthresholdselectionmethodbasedonmaximumentropyprinciple[J].TheInsti-tuteofElectricalandElectronicsEngineersTransactions,1989,SMC-19(4):866～871
[37]Otsu N,THRESHOLD A Selection method from gray-level histograms[J].IEEE Trans,1979,SMC 9(1):62～66.
[38]郑宏,潘励.基于遗传算法的图像阈值的自动选取[Ｊ].中国图形图像学报,1999,(4):327～330.
[39]Goldberg,D.E.,Samtani,M.P.Engineeringoptimizationviageneticalgorithms[c].ProceedingoftheNinthConferenceonElectronicComputation,1986,471～482.
[40付忠良.图像阈值选取方法的构造.中国图像图形学报.2000.
5:466～469
[41]刘大有等.遗传程序设计方法综述.计算机研究与发展,2001；38(2):213～222
[42]詹劲峰，戚劲峰，王海龙。基于时空马尔可夫随机场的运动目标分割技术[J]通信学报，2000,21(11):63～68
[2]王小平,曹立明. 《遗传算法—理论、应用与软件实现》.西安交通大学出版社. 2002
[3]沈庭芝,王蕾,周长志.遗传算法在小目标图像分割中的应用.系统工程与电子技术. 2002,24(12) :86～88
[4]吴成柯,刘靖,侯格贤. 图像分割的多参量遗传算法.自动化学报. 1998.3：410～413
[5]种劲松,周孝宽,王宏琦.基于遗传算法的最佳熵阈值图像分割法. 北京航空航天大学学报. 1999.6:747～750
[6]韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术 .2002.6:91～94
[7]金聪,彭嘉雄. 利用遗传算法实现数字图像分割.小型微型计算机系统. 2002.7:875～877
[8]梁光明,刘东华,李波,唐朝京.自适应阈值分割算法的改进.自动化技术与应用.第21卷第五期:43～46
[9]陈果,左洪福.图像分割的二维最大熵遗传算法.计算机辅助设计与图形学学报.2002.6:530～534
[10]贾永红. 《计算机图像处理与分析》. 武汉大学出版社. 2001
[11]耿茵茵,蔡安妮,孙景鳌. 自动图像阈值分割算法. 计算机工程与应用. 2002.17:119～122
[12]常青,王立,邢超,王红梅,李言俊. 基于遗传算法的图像阈值选取. 计算机工程与应用. 2002.22:35～37
[13]Bhandarker S M. Image Segmentation Using Evolutionary Computation. IEEE Transactions of Evolutionary Computation, 1999,3(1):1-21
[14]Kenneth R Castle. Digital Image Processing. Prentice
Hall,1995
[15]KapurJN,SahooPK,WongAKC.Anewmethodforgray-levelpicturethresholdingusingtheentropyofthehis-togram[J].ComputerVision,GraphicsandImageProcess-ing,1985(29):273～285
[16]Wang Lei,Shen Ting-Zhi, Two-Dimensional Entropy Method Based on Genetic Algorithm, Journal of Beijing Institute of Techonlogy, 2002,Vol .11,No.2
[17]章毓晋. 《图像工程(上册)图像处理和分析》.北京.清华大学出版社.1999
[18]杨淑莹. 《VC++图像处理程序设计》. 清华大学出版社. 2003
[18]陈国良等.遗传算法及其应用.人民邮电出版社,1996
[19]王培珍,杜培明,陈维南.一种用于多阈值图像自动分割的混合遗传算法[Ｊ].中国图像图形学报,2000,5(1)
[20]PunT.Anewmethodforgray-levelpicturethresholdingus-ingtheentropyofhistogram[J].SignalProcessing,1980(2):223～237
[21]JohannsenG,BileJ.Athresholdselectionmethodusingin-formationmeasures[A].In:Proceedingsofthe6thICPR,1982.140～143
[22]汪祖媛,庄镇泉,汪炳权. 红外热图像分割中的二维灰度直方图小波变换方法[Ｊ] 红外技术,2000,22(4):1～3
[23]詹劲峰,戚劲峰,王海龙. 基于时空马尔可夫随机场的运动目标分割技术[Ｊ] 通信学报,2000,21(11):63～68
[24]景晓军,蔡安妮,孙景鳌.一种基于二维最大类间方差的图像分割方法.通讯学报,2001,4:71～76
[25]刘健庄,栗文清.灰度图像的二维Ｏｓｔｕ自动阈值分割法.自动化学报,1993,19(1):101～105
[26]Brink A D. Thresholding digital images using two dimensional entropics. Pattern Recognition,1992,25(8):803～808
[27]王培珍,陈维南.基于二维阈值化与FCM相结合的图像快速分割方法.中国图形图像学报,1998,3(9):734～738
[28]Jincong.Improvegeneticalgorithmandanalysisofitsproperty〔J〕.Mini-MicroSystems,200021(9):950～952(金聪.改进型遗传算法及其性能分析〔J〕.小型微型计算机系统.2000.21(9):950～952)
[29]薛景浩,章毓晋,林行刚.二维遗传算法用于图像动态分割.自动化
学报,2000；26（5）：749-753
[30]赵荣春,迟耀斌,朱重光.图像分割技术进展.第九届全国图像图形学学术会议论文集,中国图像图形学会,1998:547～558
[31]罗希平,田捷,诸葛婴等.图像分割方法综述.模式识别与人工智能,1999,12(3):300～312
[32]李立源,龚坚,陈维南.基于二维灰度直方图最佳一维投影的图像分割方法[J].自动化学报,1996,22(3):315～322
[33]张毅军,吴雪青,夏良正.二维熵图像阈值分割的快速递推算法[J].模式识别与人工智能,1997,10(3):259～264
[34]夏良正.数字图像处理[M].南京:东南大学出版社,1999.223～228
[35]AbutalebAS.Automaticthresholdingofgray-levelpicturesusingtwo-dimensionentropy[J].ComputerVision,Graph-icsandImageProcessing,1989(47):22～32
[36]WongAKC,SahooPK.Agray-levelthresholdselectionmethodbasedonmaximumentropyprinciple[J].TheInsti-tuteofElectricalandElectronicsEngineersTransactions,1989,SMC-19(4):866～871
[37]Otsu N,THRESHOLD A Selection method from gray-level histograms[J].IEEE Trans,1979,SMC 9(1):62～66.
[38]郑宏,潘励.基于遗传算法的图像阈值的自动选取[Ｊ].中国图形图像学报,1999,(4):327～330.
[39]Goldberg,D.E.,Samtani,M.P.Engineeringoptimizationviageneticalgorithms[c].ProceedingoftheNinthConferenceonElectronicComputation,1986,471～482.
[40付忠良.图像阈值选取方法的构造.中国图像图形学报.2000.
5:466～469
[41]刘大有等.遗传程序设计方法综述.计算机研究与发展,2001；38(2):213～222
[42]詹劲峰，戚劲峰，王海龙。基于时空马尔可夫随机场的运动目标分割技术[J]通信学报，2000,21(11):63～68
© 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 |