蚁群算法及其在气象卫星云图分割中的应用
|
摘要
台风(热带气旋)是危害人类最严重的自然灾害之一,它所引起的狂风、暴雨及风暴潮等给沿海人们的生产生活带来了极大的不便和危害,同时也严重威胁到航海的安全。为了有效地降低台风对人们造成的影响,加强对台风的实时监测定位和预报就显得尤为重要。由于台风中心定位的好坏取决于台风云系的分割效果的好坏,因此对台风云系进行分割具有很高的研究价值和极其重要的现实意义。
蚁群算法作为一种新型的模拟进化算法,其良好的离散性、并行性、正反馈性和鲁棒性,使其在图像分割领域得到了广泛的应用。本文选用风云二号气象卫星拍摄的云图作为客观的资料,以2005年9月1日14时30分在福建莆田平海镇登陆的第13号台风——泰利为例,利用蚁群算法及其改进对台风云系进行分割研究,本文主要围绕以下四个方面进行研究。
论文首先对蚁群算法和图像分割方法近年来的研究进展进行了分析与总结。详细介绍了蚁群算法的基本原理及数学模型,并以TSP问题为例对蚁群算法的实现过程进行了说明。分析蚁群算法的优缺点,给出了蚁群算法在图像分割领域的一些改进措施。
其次在蚁群算法的基础上,简单介绍聚类分析的相关概念及数学描述。总结近年来有代表性的四种蚁群聚类算法,并对这几种蚁群聚类算法的基本模型及其优缺点进行介绍和分析,以基于觅食原理的蚁群聚类算法为研究重点,进行台风区域的分割研究。
根据数字图像的离散性特点,从聚类角度出发,以灰度为特征,将蚁群聚类算法引入到台风云系分割中,并通过引入初始聚类中心和引导函数来解决传统蚁群聚类算法计算量大,搜索时间过长的问题。在蚁群聚类算法的基础上,针对单纯采用蚁群聚类算法可能会将类似于台风云系的分布不均匀的无关云团分割出来而造成误检的情况,提出了一种蚁群聚类算法融合数学形态学方法的台风云系分割方法。
鉴于台风图像是自然纹理图像,论文在灰度特征的基础上,利用图像的高层次特征——纹理特征来全面地描述图像信息,以求获得更好的分割效果。通过对现有典型纹理分割方法的分析和比较,选用灰度共生矩阵法提取台风纹理特征,形成特征向量,并以其为特征,利用蚁群聚类算法进行纹理分割,给出了一种基于灰度共生矩阵的台风图像分割方法。
最后采用MATLAB7.1作为编程工具,对本文算法的有效性和准确性进行仿真验证。实验结果表明,本文的算法能够有效地对台风云系进行分割及特征提取,进而能很好的实现对台风中心定位,其研究成果对台风云系的识别、预报及定位等具有一定的现实意义。
Typhoon (tropical cyclone) is one of the worst natural disasters that seriously influence human being. Strong winds, heavy rain, storm surge and other disasters caused by Typhoon have brought great inconvenience and danger to people's production and life nearby southeast of sea in our country, even seriously threaten to the sailing security. In order to reduce disasters effectively caused by typhoon, reinforcing the real-time monitoring, location and forecasting for the typhoon is particularly important. Due to accuracy of the typhoon centre locating mainly depends on the segmentation effect of Typhoon. Therefore, the typhoon segmentation was highly valuable to study and extremely important practical significance.
Ant colony algorithm is a new simulated evolutionary algorithm. Its characters of discreteness, parallelism, positive feedback and robustness make it get widely application in the image segmentation field. This paper selects FY-2 meteorological satellite cloud pictures as subject investigated,13th typhoon—TALIM as an example which landed PingHai town, PuTian city, FuJian province at 14:30 of September 1st 2005. Ant colony algorithm and its improvement are applied to the research of the typhoon segmentation, and this paper mainly involves the following four aspects of works:
Firstly the research progress of ant colony algorithm and image segmentation in recent years is summarized. The principle and mathematical model of ant colony algorithm is deeply analyzed and elucidated. The realization process of ant colony algorithm is explained by solving the TSP problem. Finally, some improved algorithms of ant colony algorithm widely used in the image segmentation field are quoted.
Secondly the related concepts and mathematical description of cluster analysis is briefly illuminated, and then some representative ant colony clustering algorithms in recent years are summarized. After that, four basic models are introduced briefly and merits and drawbacks of ACCA are compared. Ant colony clustering algorithm which based on the principle of foraging is used to segment the typhoon image.
According to the discrete characteristics of digital images, the ant colony clustering algorithm is applied to the segmentation of the typhoon from view of the clustering. By introduced the initial clustering centers and guidance function, the large calculation and the search time of traditional ant colony clustering algorithm can be shorten obviously. The problem of low accuracy may be caused by the uneven distribution of unrelated clouds which is similar to typhoon when the ant colony algorithm is utilized respectively. To solve the problem, an ant colony algorithm integrated with mathematical morphology of typhoon segmentation is presented.
Considering the typhoon image is a natural texture image, based on the grayscale characteristics, using the high-level image features--texture features can describe fully the image information for better segmentation results. Texture features of typhoon image are extracted by using GLCM and the feature vector formed.Then the typhoon-cloudy is separated from motley cloudy by using ant colony clustering algorithm.
By using MATLAB7.1 as a programming tool, the effectively and accuracy of algorithm has to be tested and verified. Experiments also show that the algorithm of this article is effective to segment the typhoon-cloudy and extract the feature of typhoon area, and finally realize the location of typhoon center. The result of its research has certain practical significance for identification, forecasting and location of typhoon.
蚁群算法作为一种新型的模拟进化算法,其良好的离散性、并行性、正反馈性和鲁棒性,使其在图像分割领域得到了广泛的应用。本文选用风云二号气象卫星拍摄的云图作为客观的资料,以2005年9月1日14时30分在福建莆田平海镇登陆的第13号台风——泰利为例,利用蚁群算法及其改进对台风云系进行分割研究,本文主要围绕以下四个方面进行研究。
论文首先对蚁群算法和图像分割方法近年来的研究进展进行了分析与总结。详细介绍了蚁群算法的基本原理及数学模型,并以TSP问题为例对蚁群算法的实现过程进行了说明。分析蚁群算法的优缺点,给出了蚁群算法在图像分割领域的一些改进措施。
其次在蚁群算法的基础上,简单介绍聚类分析的相关概念及数学描述。总结近年来有代表性的四种蚁群聚类算法,并对这几种蚁群聚类算法的基本模型及其优缺点进行介绍和分析,以基于觅食原理的蚁群聚类算法为研究重点,进行台风区域的分割研究。
根据数字图像的离散性特点,从聚类角度出发,以灰度为特征,将蚁群聚类算法引入到台风云系分割中,并通过引入初始聚类中心和引导函数来解决传统蚁群聚类算法计算量大,搜索时间过长的问题。在蚁群聚类算法的基础上,针对单纯采用蚁群聚类算法可能会将类似于台风云系的分布不均匀的无关云团分割出来而造成误检的情况,提出了一种蚁群聚类算法融合数学形态学方法的台风云系分割方法。
鉴于台风图像是自然纹理图像,论文在灰度特征的基础上,利用图像的高层次特征——纹理特征来全面地描述图像信息,以求获得更好的分割效果。通过对现有典型纹理分割方法的分析和比较,选用灰度共生矩阵法提取台风纹理特征,形成特征向量,并以其为特征,利用蚁群聚类算法进行纹理分割,给出了一种基于灰度共生矩阵的台风图像分割方法。
最后采用MATLAB7.1作为编程工具,对本文算法的有效性和准确性进行仿真验证。实验结果表明,本文的算法能够有效地对台风云系进行分割及特征提取,进而能很好的实现对台风中心定位,其研究成果对台风云系的识别、预报及定位等具有一定的现实意义。
Typhoon (tropical cyclone) is one of the worst natural disasters that seriously influence human being. Strong winds, heavy rain, storm surge and other disasters caused by Typhoon have brought great inconvenience and danger to people's production and life nearby southeast of sea in our country, even seriously threaten to the sailing security. In order to reduce disasters effectively caused by typhoon, reinforcing the real-time monitoring, location and forecasting for the typhoon is particularly important. Due to accuracy of the typhoon centre locating mainly depends on the segmentation effect of Typhoon. Therefore, the typhoon segmentation was highly valuable to study and extremely important practical significance.
Ant colony algorithm is a new simulated evolutionary algorithm. Its characters of discreteness, parallelism, positive feedback and robustness make it get widely application in the image segmentation field. This paper selects FY-2 meteorological satellite cloud pictures as subject investigated,13th typhoon—TALIM as an example which landed PingHai town, PuTian city, FuJian province at 14:30 of September 1st 2005. Ant colony algorithm and its improvement are applied to the research of the typhoon segmentation, and this paper mainly involves the following four aspects of works:
Firstly the research progress of ant colony algorithm and image segmentation in recent years is summarized. The principle and mathematical model of ant colony algorithm is deeply analyzed and elucidated. The realization process of ant colony algorithm is explained by solving the TSP problem. Finally, some improved algorithms of ant colony algorithm widely used in the image segmentation field are quoted.
Secondly the related concepts and mathematical description of cluster analysis is briefly illuminated, and then some representative ant colony clustering algorithms in recent years are summarized. After that, four basic models are introduced briefly and merits and drawbacks of ACCA are compared. Ant colony clustering algorithm which based on the principle of foraging is used to segment the typhoon image.
According to the discrete characteristics of digital images, the ant colony clustering algorithm is applied to the segmentation of the typhoon from view of the clustering. By introduced the initial clustering centers and guidance function, the large calculation and the search time of traditional ant colony clustering algorithm can be shorten obviously. The problem of low accuracy may be caused by the uneven distribution of unrelated clouds which is similar to typhoon when the ant colony algorithm is utilized respectively. To solve the problem, an ant colony algorithm integrated with mathematical morphology of typhoon segmentation is presented.
Considering the typhoon image is a natural texture image, based on the grayscale characteristics, using the high-level image features--texture features can describe fully the image information for better segmentation results. Texture features of typhoon image are extracted by using GLCM and the feature vector formed.Then the typhoon-cloudy is separated from motley cloudy by using ant colony clustering algorithm.
By using MATLAB7.1 as a programming tool, the effectively and accuracy of algorithm has to be tested and verified. Experiments also show that the algorithm of this article is effective to segment the typhoon-cloudy and extract the feature of typhoon area, and finally realize the location of typhoon center. The result of its research has certain practical significance for identification, forecasting and location of typhoon.
引文
[1]陈渭民.卫星气象学[M].北京：气象出版社,2003：1-5页.
[2]王丕诰,刘宗义,张开斗.应用卫星气象学[M].青岛：中国海洋大学出版社,2004：1-8页.
[3]余建波.基于气象卫星云图的云类识别及台风分割和中心定位研究[D].武汉理工大学工学硕士学位论文.2008：1-3页.
[4]彭光龙.基于卫星云图的台风识别和定位研究[D].成都信息工程学院硕士学位论文.2007：Ⅰ-Ⅱ页.
[5]黄竞伟,朱福喜,康立山.计算智能[M].北京：科学出版社,2010：111-127页.
[6]韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术.2002,24(6)：91-94页.
[7]乐宋进,和雷,泳芬.图像分割方法的研究现状与展望[J].南昌水专学报.2004,23(2)：15-20页.
[8]杨合超,周雪梅.几种图像分割技术的比较[J].电脑知识与技术.2009,5(9)：440-2441页.
[9]郭文强,侯勇严.数字图像处理[M].西安：西安电子科技大学出版社,2009：164-190,210-212页.
[10]杨治明,王晓蓉,陈应祖.基于BP人工神经网络图像分割技术[J].计算机应用.2006,26：145-146页.
[11]杨治明,王晓蓉,彭军等.BP人工神经网络在图像分割中的应用[J].计算机科学.2007,34(13)：234-236页.
[12]赵敏.基于小波变换的图像分割研究[D].武汉大学硕士学位论文.2003：1-15页.
[13]Changjiang Zhang, Chunjiang Duanmu, HuiYu Chen. Typhoon image segmentation by combining curvelet transform with continuous wavelet transform[C]//Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China,2-4 Nov.2007:1512-1517p.
[14]文华.基于数学形态学的图像处理算法的研究[D].哈尔滨工程大学硕士学位论文.2007：1-15页.
[15]王果,段汕.灰度形态学在图像分析方面的应用[J].图形学与辅助设计(软件导刊).2007,10：121-122页.
[16]吴成柯,刘靖,徐正伟等.图像分割的遗传算法方法[J].西安电子科技大学学报.1996,23(1)：34-40页.
[17]陈杰,阜艳.基于遗传算法的图像分割的研究[J].现代电子技术.2010,33(14)：42-44页.
[18]Changjiang Zhang, Xiaoqin Lu, Juan Lu, etc. Segmentation for Main Body of Typhoon from Satellite Cloud Image by Genetic Algorithm in Contourlet Domain[C]. Third 2008 International Conference on Convergence and Hybrid Information Technology,2008:352-357p.
[19]夏勇.基于特征的纹理图像分割技术研究[D].西北工业大学博士学位论文.2006：1-10页.
[20]杨淑莹.模式识别与智能计算:Matlab技术实现[M].北京：电子工业出版社,2008：319-336页.
[21]Dorigo M, Bonabeau E, Theraulaz G. Ant algorithms and stigmergy [J]. Future Generation Computer Systems,2000,16:851-871p.
[22]Mehdi Hosseinzadeh Aghdam, Nasser Ghasem-Aghaee, Mohammad Ehsan Basiri. Text feature selection using ant colony optimization [J]. Expert Systems with Applications,2009,36:6843-6853p.
[23]JinWei Xu, Ping Wang, YiYang Xie. Image Segmentation of typhoon spiral cloud sands based on support vector machine[C]//Proceedings of the Eighth International Conference on Machine Learning and Cybernetics,2009:1088-1093p.
[24]薛琴,陈玮,罗俊奇.基于梯度算子的蚁群图像分割算法研究[J].计算机工程与设计.2007,28(23)：5660-5663页.
[25]刘凯,黄峰,寇正.基于纹理和区域特征的台风卫星云图分割方法.计算机工程与应用[J].2004,40(33)：219-220页.
[26]Xin Zhao, Myung-Eun Lee, Soo-Hyung Kim. Improved Image Thresholding using Ant Colony Optimization Algorithm[C]. International Conference on Advanced Language Processing and Web Information Technology,2008:210-215p.
[27]韩彦芳,施鹏飞.基于蚁群算法的图像分割方法[J].计算机工程与应用.2004,18：5-7页.
[28]R.J.Mullen, D. Monekosso, S. Barman, P. Remagnino. A review of ant algorithms [J]. Expert Systems with Applications.2009,36:9608-9617p.
[29]黄友锐.智能优化算法及其应用[M].北京：国防工业出版社,2008：119-139页.
[30]段海滨著.蚁群算法原理及其应用[M].北京：科学出版社,2005：1-42,100-169页.
[31]李士勇等编著.蚁群算法及其应用[M].哈尔滨：哈尔滨工业大学出版 社,2004：53-194页.
[32]陈峻,秦玲,陈宏建等.具有感觉和知觉特征的蚁群算法[J].系统仿真学报.2003,15(10)：1418-1425页.
[33]王颖,谢剑英.一种自适应蚁群算法及其仿真研究[J].系统仿真学报.2002,14(1)：30-33页.
[34]刘峡壁.人工智能导论——方法与系统[M].北京：国防工业出版社,2008：257-262页.
[35]王宏生,孟国艳.人工智能及其应用[M].北京：国防工业出版社,2009：178-181页.
[36]冯祖仁,李进,冯远静.分散、递阶蚁群算法及其在相变序列图像分割中的应用[J].西安交通大学学报.2007,41(2)：136-140页.
[37]卢珏.基于自适应蚁群算法的图像分割[J]. ITS通讯.2005,(4)：31：33页.
[38]凌六一,黄友锐.基于混沌蚁群算法的快速红外图像分割[J].激光与红外.2010,40(6)：679-682页.
[39]方新,赵卫东,杨晓春.基于Ant-Tree聚类算法的图像分割[J].计算机应用.2008,28(5)：1240-1243页.
[40]Channa, A. H., Rajpoot, N. M., & Rajpoot, K. M. (2006). Texture segmentation using ant tree clustering[C]. In 2006 IEEE international conference on engineering of intelligent systems (pp.1-6).
[41]王振青.基于蚁群算法的图像分割方法研究[D].中国石油大学(华东)硕士学位论文.2009：50-60页.
[42]王爽,黄友锐,李冬.基于蚁群算法的改进Otsu理论的图像多阈值分割[J].微计算机应用.2008,29(4)：25-28页.
[43]杨卫莉,郭雷,许钟等.基于区域生长和蚁群聚类的图像分割技术[J].计算机应用研究.2008,25(5)：1579-1581页.
[44]王晓年,冯远静,冯祖仁.一种基于主动轮廓模型的蚁群图像分割算法[J].控制理论与应用.2006,23(4)：515-522页.
[45]张锋,卿粼波,王旭阳等.基于遗传算法和蚂蚁算法的图象分割[J].四川大学学报(自然科学版).2005,42(4)：735-738页.
[46]卢晓东,周凤岐,周军.马尔可夫随机场中应用蚁群系统的红外图像分割[J].火力与指挥控制.2006,31(7)：86-89页.
[47]元昌安.数据挖掘原理与SPSS Clementine应用宝典[M].北京：电子工业出版社,2009：101-108页.
[48]裴振奎,李华,宋建伟等.蚁群聚类算法研究及应用[J].计算机工程与设计.2008, 29(19)：5009-5013页.
[49]P.S. Shelokar, V.K. Jayaraman, B.D. Kulkarni. An ant colony approach for clustering [J]. Analytica Chimica Acta,2004,509:187-195p.
[50]孙即祥.现代模式识别(第二版)[M].北京：高等教育出版社,2008：18-30页.
[51]朱峰.蚁群算法在聚类分析中的应用研究[D].西北大学硕士毕业论文.2009：9-12页.
[52]Han Jiawei, Kamber Micheline. Data Mining Concepts and Techniques [J].2nd edition, San Francisco USA:Morgan Kaufmann Publisher,2000:1-6,335-338p.
[53]张建华,江贺,张宪超.蚁群聚类算法综述[J].计算机工程与应用.2006：171-174页.
[54]李燕.蚁群聚类算法研究现状的分析[J].中国科技信息.2009,9：114-118页.
[55]高尚,杨静宇.群智能算法及其应用[M].北京：中国水利水电出版社,2006：43-50页.
[56]杨欣斌,孙京诰,黄道.一种进化聚类学习新方法[J].计算机工程与应用.2003,15：60-62页.
[57]王虹,余建波,陈明明等.基于FY-2C气象卫星云图的台风分割方法的研究[J].计算机工程与应用.2008,44(20)：188-191页.
[58]胡学龙,许开宇.数字图像处理[M].北京：电子工业出版社,2006：170-178页.
[59]范立南,韩晓微,张广渊.图像处理与模式识别[M].北京：科学出版社,2007：62-65页.
[60]Q.P. ZHANG, L.L. LAI, H. WEI, etc. Non-clear Typhoon Eye Tracking by Artificial Ant colony[C]//Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian,2006:4063-4068p.
[61]邵永波,张荣国,邢益良等.基于置换群的遥感图像边缘检测[J].计算机仿真.2010,27(1)：214-217页.
[62]YANFANG HAN, PENGFEI SHI. An Improved Ant Colony Algorithm for Fuzzy Clustering in Image Segmentation [J]. Neurocomputing,2007,70 (4/6):665-671页.
[63]曾志远.卫星遥感图像计算机分类与地学应用研究[M].北京：科学出版社,2004：40-48,69-73页.
[64]Randen R C, Husoy J H. Filtering for texture classification:a comparative study [J].IEEE Trans Pattern Anal Mach Intel,1999,21 (4):291-310p.
[65]马莉,范影乐著.纹理图像分析[M].北京：科学出版社,2009：3-51页.
[66]毛伟民.纹理图像分割算法的研究[D].苏州大学硕士学位论文.2009：12-16页.
[67]苑丽红,付丽,杨勇.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用.2009,29(4)：1018-1021页.
[68]Leen-Kiat Soh, Costas Tsatsoulis. Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co-Occurrence Matrices [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,1999,37(2):780-795p.
[69]王辉.基于灰度共生矩阵本材表面纹理模式识别方法的研究[D].东北林业大学硕士学位论文.2007：15-25页.
[70]Haralick R M, Shapiro L G. Computer and Robot Vision, Addison-Wesley,1992.
[71]Engin Avci, Abdulkadir Sengur, Davut Hanbay. An optimum feature extraction method for texture classification [J]. Expert Systems with Applications,2009,36:6036-6043页.
[72]曾伟.一种用于图像分割的改进FCM聚类算法[J].电子测量技术.2006,29(5)：46-48页.
[73]Kim K I, Jung K, Park S H et al. Support vector machines for texture classification [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002,24(11):1542-1550p.
[74]Liu Kai, Huang Feng, and Luo Jian, The study on the method of typhoon satellite image segmentation [J]. Micro-Computer Development. No.1, pp.54-55,2001.
[75]Chellappa, R., Chatterjee, S., & Bagdazian, R. (1985). Classification of textures using Gaussian Markov random fields [J]. IEEE Transactions on Acoustics, Speech and Signal Processing,30,959-963p.
[76]X. Zhuang. Image Feature Extraction with the Perceptual Graph Based on the Ant Colony System[C].2004 IEEE International Conference on Systems, Man and Cybernetics:6354-6359p.
[77]David A. Clausi, Yong ping Zhao. Rapid extraction of image texture by co-occurrence using a hybrid data structure [J]. Computers & Geosciences 2002, 28:763-774p.
[78]Yong Hu, Chun xia Zhao, Hong nan Wang. Directional Analysis of Texture Images Using Gray Level Co-occurrence Matrix[C].2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application,2008:277-281p.
[2]王丕诰,刘宗义,张开斗.应用卫星气象学[M].青岛：中国海洋大学出版社,2004：1-8页.
[3]余建波.基于气象卫星云图的云类识别及台风分割和中心定位研究[D].武汉理工大学工学硕士学位论文.2008：1-3页.
[4]彭光龙.基于卫星云图的台风识别和定位研究[D].成都信息工程学院硕士学位论文.2007：Ⅰ-Ⅱ页.
[5]黄竞伟,朱福喜,康立山.计算智能[M].北京：科学出版社,2010：111-127页.
[6]韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术.2002,24(6)：91-94页.
[7]乐宋进,和雷,泳芬.图像分割方法的研究现状与展望[J].南昌水专学报.2004,23(2)：15-20页.
[8]杨合超,周雪梅.几种图像分割技术的比较[J].电脑知识与技术.2009,5(9)：440-2441页.
[9]郭文强,侯勇严.数字图像处理[M].西安：西安电子科技大学出版社,2009：164-190,210-212页.
[10]杨治明,王晓蓉,陈应祖.基于BP人工神经网络图像分割技术[J].计算机应用.2006,26：145-146页.
[11]杨治明,王晓蓉,彭军等.BP人工神经网络在图像分割中的应用[J].计算机科学.2007,34(13)：234-236页.
[12]赵敏.基于小波变换的图像分割研究[D].武汉大学硕士学位论文.2003：1-15页.
[13]Changjiang Zhang, Chunjiang Duanmu, HuiYu Chen. Typhoon image segmentation by combining curvelet transform with continuous wavelet transform[C]//Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China,2-4 Nov.2007:1512-1517p.
[14]文华.基于数学形态学的图像处理算法的研究[D].哈尔滨工程大学硕士学位论文.2007：1-15页.
[15]王果,段汕.灰度形态学在图像分析方面的应用[J].图形学与辅助设计(软件导刊).2007,10：121-122页.
[16]吴成柯,刘靖,徐正伟等.图像分割的遗传算法方法[J].西安电子科技大学学报.1996,23(1)：34-40页.
[17]陈杰,阜艳.基于遗传算法的图像分割的研究[J].现代电子技术.2010,33(14)：42-44页.
[18]Changjiang Zhang, Xiaoqin Lu, Juan Lu, etc. Segmentation for Main Body of Typhoon from Satellite Cloud Image by Genetic Algorithm in Contourlet Domain[C]. Third 2008 International Conference on Convergence and Hybrid Information Technology,2008:352-357p.
[19]夏勇.基于特征的纹理图像分割技术研究[D].西北工业大学博士学位论文.2006：1-10页.
[20]杨淑莹.模式识别与智能计算:Matlab技术实现[M].北京：电子工业出版社,2008：319-336页.
[21]Dorigo M, Bonabeau E, Theraulaz G. Ant algorithms and stigmergy [J]. Future Generation Computer Systems,2000,16:851-871p.
[22]Mehdi Hosseinzadeh Aghdam, Nasser Ghasem-Aghaee, Mohammad Ehsan Basiri. Text feature selection using ant colony optimization [J]. Expert Systems with Applications,2009,36:6843-6853p.
[23]JinWei Xu, Ping Wang, YiYang Xie. Image Segmentation of typhoon spiral cloud sands based on support vector machine[C]//Proceedings of the Eighth International Conference on Machine Learning and Cybernetics,2009:1088-1093p.
[24]薛琴,陈玮,罗俊奇.基于梯度算子的蚁群图像分割算法研究[J].计算机工程与设计.2007,28(23)：5660-5663页.
[25]刘凯,黄峰,寇正.基于纹理和区域特征的台风卫星云图分割方法.计算机工程与应用[J].2004,40(33)：219-220页.
[26]Xin Zhao, Myung-Eun Lee, Soo-Hyung Kim. Improved Image Thresholding using Ant Colony Optimization Algorithm[C]. International Conference on Advanced Language Processing and Web Information Technology,2008:210-215p.
[27]韩彦芳,施鹏飞.基于蚁群算法的图像分割方法[J].计算机工程与应用.2004,18：5-7页.
[28]R.J.Mullen, D. Monekosso, S. Barman, P. Remagnino. A review of ant algorithms [J]. Expert Systems with Applications.2009,36:9608-9617p.
[29]黄友锐.智能优化算法及其应用[M].北京：国防工业出版社,2008：119-139页.
[30]段海滨著.蚁群算法原理及其应用[M].北京：科学出版社,2005：1-42,100-169页.
[31]李士勇等编著.蚁群算法及其应用[M].哈尔滨：哈尔滨工业大学出版 社,2004：53-194页.
[32]陈峻,秦玲,陈宏建等.具有感觉和知觉特征的蚁群算法[J].系统仿真学报.2003,15(10)：1418-1425页.
[33]王颖,谢剑英.一种自适应蚁群算法及其仿真研究[J].系统仿真学报.2002,14(1)：30-33页.
[34]刘峡壁.人工智能导论——方法与系统[M].北京：国防工业出版社,2008：257-262页.
[35]王宏生,孟国艳.人工智能及其应用[M].北京：国防工业出版社,2009：178-181页.
[36]冯祖仁,李进,冯远静.分散、递阶蚁群算法及其在相变序列图像分割中的应用[J].西安交通大学学报.2007,41(2)：136-140页.
[37]卢珏.基于自适应蚁群算法的图像分割[J]. ITS通讯.2005,(4)：31：33页.
[38]凌六一,黄友锐.基于混沌蚁群算法的快速红外图像分割[J].激光与红外.2010,40(6)：679-682页.
[39]方新,赵卫东,杨晓春.基于Ant-Tree聚类算法的图像分割[J].计算机应用.2008,28(5)：1240-1243页.
[40]Channa, A. H., Rajpoot, N. M., & Rajpoot, K. M. (2006). Texture segmentation using ant tree clustering[C]. In 2006 IEEE international conference on engineering of intelligent systems (pp.1-6).
[41]王振青.基于蚁群算法的图像分割方法研究[D].中国石油大学(华东)硕士学位论文.2009：50-60页.
[42]王爽,黄友锐,李冬.基于蚁群算法的改进Otsu理论的图像多阈值分割[J].微计算机应用.2008,29(4)：25-28页.
[43]杨卫莉,郭雷,许钟等.基于区域生长和蚁群聚类的图像分割技术[J].计算机应用研究.2008,25(5)：1579-1581页.
[44]王晓年,冯远静,冯祖仁.一种基于主动轮廓模型的蚁群图像分割算法[J].控制理论与应用.2006,23(4)：515-522页.
[45]张锋,卿粼波,王旭阳等.基于遗传算法和蚂蚁算法的图象分割[J].四川大学学报(自然科学版).2005,42(4)：735-738页.
[46]卢晓东,周凤岐,周军.马尔可夫随机场中应用蚁群系统的红外图像分割[J].火力与指挥控制.2006,31(7)：86-89页.
[47]元昌安.数据挖掘原理与SPSS Clementine应用宝典[M].北京：电子工业出版社,2009：101-108页.
[48]裴振奎,李华,宋建伟等.蚁群聚类算法研究及应用[J].计算机工程与设计.2008, 29(19)：5009-5013页.
[49]P.S. Shelokar, V.K. Jayaraman, B.D. Kulkarni. An ant colony approach for clustering [J]. Analytica Chimica Acta,2004,509:187-195p.
[50]孙即祥.现代模式识别(第二版)[M].北京：高等教育出版社,2008：18-30页.
[51]朱峰.蚁群算法在聚类分析中的应用研究[D].西北大学硕士毕业论文.2009：9-12页.
[52]Han Jiawei, Kamber Micheline. Data Mining Concepts and Techniques [J].2nd edition, San Francisco USA:Morgan Kaufmann Publisher,2000:1-6,335-338p.
[53]张建华,江贺,张宪超.蚁群聚类算法综述[J].计算机工程与应用.2006：171-174页.
[54]李燕.蚁群聚类算法研究现状的分析[J].中国科技信息.2009,9：114-118页.
[55]高尚,杨静宇.群智能算法及其应用[M].北京：中国水利水电出版社,2006：43-50页.
[56]杨欣斌,孙京诰,黄道.一种进化聚类学习新方法[J].计算机工程与应用.2003,15：60-62页.
[57]王虹,余建波,陈明明等.基于FY-2C气象卫星云图的台风分割方法的研究[J].计算机工程与应用.2008,44(20)：188-191页.
[58]胡学龙,许开宇.数字图像处理[M].北京：电子工业出版社,2006：170-178页.
[59]范立南,韩晓微,张广渊.图像处理与模式识别[M].北京：科学出版社,2007：62-65页.
[60]Q.P. ZHANG, L.L. LAI, H. WEI, etc. Non-clear Typhoon Eye Tracking by Artificial Ant colony[C]//Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian,2006:4063-4068p.
[61]邵永波,张荣国,邢益良等.基于置换群的遥感图像边缘检测[J].计算机仿真.2010,27(1)：214-217页.
[62]YANFANG HAN, PENGFEI SHI. An Improved Ant Colony Algorithm for Fuzzy Clustering in Image Segmentation [J]. Neurocomputing,2007,70 (4/6):665-671页.
[63]曾志远.卫星遥感图像计算机分类与地学应用研究[M].北京：科学出版社,2004：40-48,69-73页.
[64]Randen R C, Husoy J H. Filtering for texture classification:a comparative study [J].IEEE Trans Pattern Anal Mach Intel,1999,21 (4):291-310p.
[65]马莉,范影乐著.纹理图像分析[M].北京：科学出版社,2009：3-51页.
[66]毛伟民.纹理图像分割算法的研究[D].苏州大学硕士学位论文.2009：12-16页.
[67]苑丽红,付丽,杨勇.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用.2009,29(4)：1018-1021页.
[68]Leen-Kiat Soh, Costas Tsatsoulis. Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co-Occurrence Matrices [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,1999,37(2):780-795p.
[69]王辉.基于灰度共生矩阵本材表面纹理模式识别方法的研究[D].东北林业大学硕士学位论文.2007：15-25页.
[70]Haralick R M, Shapiro L G. Computer and Robot Vision, Addison-Wesley,1992.
[71]Engin Avci, Abdulkadir Sengur, Davut Hanbay. An optimum feature extraction method for texture classification [J]. Expert Systems with Applications,2009,36:6036-6043页.
[72]曾伟.一种用于图像分割的改进FCM聚类算法[J].电子测量技术.2006,29(5)：46-48页.
[73]Kim K I, Jung K, Park S H et al. Support vector machines for texture classification [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002,24(11):1542-1550p.
[74]Liu Kai, Huang Feng, and Luo Jian, The study on the method of typhoon satellite image segmentation [J]. Micro-Computer Development. No.1, pp.54-55,2001.
[75]Chellappa, R., Chatterjee, S., & Bagdazian, R. (1985). Classification of textures using Gaussian Markov random fields [J]. IEEE Transactions on Acoustics, Speech and Signal Processing,30,959-963p.
[76]X. Zhuang. Image Feature Extraction with the Perceptual Graph Based on the Ant Colony System[C].2004 IEEE International Conference on Systems, Man and Cybernetics:6354-6359p.
[77]David A. Clausi, Yong ping Zhao. Rapid extraction of image texture by co-occurrence using a hybrid data structure [J]. Computers & Geosciences 2002, 28:763-774p.
[78]Yong Hu, Chun xia Zhao, Hong nan Wang. Directional Analysis of Texture Images Using Gray Level Co-occurrence Matrix[C].2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application,2008:277-281p.
© 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 |