红外图像中车辆目标识别方法研究
|
摘要
红外技术在21世纪的军事和民用等各个领域发挥着至关重要的作用,而且随着未来战场的需要和国民经济的不断发展,红外技术将发挥着越来越重要的作用。其中红外目标识别技术是世界各国学者研究的前沿和热点问题之一。本文根据红外目标自动识别系统(ATR)的特点,在红外车辆目标的对比度增强、自动分割、特征提取、目标识别等方面,进行了较为系统的研究。本文的主要研究内容如下:
1)基于遗传算法的红外图像自适应模糊增强。由于红外车辆目标在成像过程中存在许多不确定性即模糊性,针对红外图像的模糊性将模糊理论运用到红外图像,提出了一种基于模糊理论的图像质量测度函数,把它作为遗传算法的适应度函数对非完全Beta函数的α和β参数进行自适应动态调节来拟合几种典型的灰度变换曲线,实现感兴趣区域红外车辆目标的自适应模糊增强。实验结果表明了该方法的合理性和有效性,在性能上优于传统的图像增强技术和现有的一些同类增强技术,具有较高的自适应性和智能性。
2)基于遗传算法的红外车辆目标自动模糊分割。针对红外图像的特点,提出了一种基于遗传算法的自动模糊分割红外车辆目标图像的方法。首先选取图像中包含待分割的车辆目标的感兴趣区域以加快运算速度;然后对感兴趣区域图像进行模糊增强,借助于二维OTSU方法对增强后的感兴趣区域进行阈值分割。为了加快分割算法的速度,先限定一个最佳阈值取值空间,再利用遗传算法在此阈值空间内自动搜索最佳分割阈值;为了弥补单独利用二维OTSU方法分割的不足,采用缩短模糊边缘宽度的方法来提取感兴趣区域红外车辆目标图像的边缘。把二维OTSU方法分割的图像与模糊边缘提取得到的边缘图像进行或运算,最后进行填充以得到最终的车辆目标分割图像。实验结果表明:这种自动模糊分割技术比一维OTSU和二维OTSU算法能得到更准确和完整的车辆目标。
3)基于径向基神经网络的红外车辆目标识别。给出一种基于径向基(RBF)神经网络的车辆目标识别算法。该方法提取平移、旋转、尺度放缩等变换下都不变的目标形状特征,其中包括8个离散余弦变换描述子,6个独立的不变矩,3个最能区别目标特征的区域描述子,把这些特征参数输入RBF神经网络进行分类识别。实验结果表明,这种RBF网络的特征融合识别方法性能稳定,比BP网络速度快,且较BP网络具有更高的识别精度。
In 21 century, infrared technology is valuable in military and civilian domains. With the demand of battlefield in the future and the development of country economy, the infrared technology will be more and more important. Infrared target recognition is one of the hot problems for scholars in the world. Based on the features of infrared automatic target recognition, this paper has made some systematic studies in infrared vehicle target recognition, such as preprocessing of infrared vehicle target images, contrast enhancement, automatic segmentation, features extraction and target recognition, etc.. The main works of this paper are as follows:
1) Adaptive fuzzy infrared image enhancement based on genetic algorithm. Because there are uncertainties, that is to say, fuzziness in the infrared vehicle target image, fuzzy theory is used in the infrared image processing. A new kind of image measure function is presented by fuzzy theory. We use it as the fitness function of genetic algorithm to adaptively optimize parameterαandβin in-complete Beta function. Thus an optimal gray transformation curve is obtained to enhance the region of interest in an infrared vehicle target image. Experimental results show that this method has high adaptability and intelligence. The proposed method is better than classical image enhancement methods and some existing similar methods.
2) Automatic fuzzy segmentation for infrared vehicle target based on genetic algorithm. According to the characteristic of infrared images, a new auto(?)atic fuzzy segmentation method is presented based on genetic algorithm to segment vehicle target from an infrared image. Firstly, a region of interest (ROI) is selected in order to reduce computation cost. Secondly, the ROI is enhanced by fuzzy algorithm. Thirdly, 2D Maximum Between-cluster Variance algorithm is applied to segment the ROI. At the same time, the genetic algorithm is combined with 2D MBV to make the calculation faster by its capacity of searching the best answer in a threshold space. Then we detect fuzzy edge based on shortening width of fuzzy edge. The final segmentation image can be obtained by OR and filling operations for the segmented region by combining 2D MBV with fuzzy edge. Exper(?)mental results show that the new method can get higher well and truly vehicle target than 1D OTSU or 2D OTSU.
3) Infrared vehicle target recognition based on RBF network. A vehicle recognition approach is proposed based on radial basis function (RBF) neural Network. It extracts the invariant features for translation, rotation, and scale change of vehicle targets: 8 discrete cosine transformation descriptors, 6 independent invariant moments and 3 region characterizations. Compared with BP network, the RBF Network is faster and has higher recognition rate.
1)基于遗传算法的红外图像自适应模糊增强。由于红外车辆目标在成像过程中存在许多不确定性即模糊性,针对红外图像的模糊性将模糊理论运用到红外图像,提出了一种基于模糊理论的图像质量测度函数,把它作为遗传算法的适应度函数对非完全Beta函数的α和β参数进行自适应动态调节来拟合几种典型的灰度变换曲线,实现感兴趣区域红外车辆目标的自适应模糊增强。实验结果表明了该方法的合理性和有效性,在性能上优于传统的图像增强技术和现有的一些同类增强技术,具有较高的自适应性和智能性。
2)基于遗传算法的红外车辆目标自动模糊分割。针对红外图像的特点,提出了一种基于遗传算法的自动模糊分割红外车辆目标图像的方法。首先选取图像中包含待分割的车辆目标的感兴趣区域以加快运算速度;然后对感兴趣区域图像进行模糊增强,借助于二维OTSU方法对增强后的感兴趣区域进行阈值分割。为了加快分割算法的速度,先限定一个最佳阈值取值空间,再利用遗传算法在此阈值空间内自动搜索最佳分割阈值;为了弥补单独利用二维OTSU方法分割的不足,采用缩短模糊边缘宽度的方法来提取感兴趣区域红外车辆目标图像的边缘。把二维OTSU方法分割的图像与模糊边缘提取得到的边缘图像进行或运算,最后进行填充以得到最终的车辆目标分割图像。实验结果表明:这种自动模糊分割技术比一维OTSU和二维OTSU算法能得到更准确和完整的车辆目标。
3)基于径向基神经网络的红外车辆目标识别。给出一种基于径向基(RBF)神经网络的车辆目标识别算法。该方法提取平移、旋转、尺度放缩等变换下都不变的目标形状特征,其中包括8个离散余弦变换描述子,6个独立的不变矩,3个最能区别目标特征的区域描述子,把这些特征参数输入RBF神经网络进行分类识别。实验结果表明,这种RBF网络的特征融合识别方法性能稳定,比BP网络速度快,且较BP网络具有更高的识别精度。
In 21 century, infrared technology is valuable in military and civilian domains. With the demand of battlefield in the future and the development of country economy, the infrared technology will be more and more important. Infrared target recognition is one of the hot problems for scholars in the world. Based on the features of infrared automatic target recognition, this paper has made some systematic studies in infrared vehicle target recognition, such as preprocessing of infrared vehicle target images, contrast enhancement, automatic segmentation, features extraction and target recognition, etc.. The main works of this paper are as follows:
1) Adaptive fuzzy infrared image enhancement based on genetic algorithm. Because there are uncertainties, that is to say, fuzziness in the infrared vehicle target image, fuzzy theory is used in the infrared image processing. A new kind of image measure function is presented by fuzzy theory. We use it as the fitness function of genetic algorithm to adaptively optimize parameterαandβin in-complete Beta function. Thus an optimal gray transformation curve is obtained to enhance the region of interest in an infrared vehicle target image. Experimental results show that this method has high adaptability and intelligence. The proposed method is better than classical image enhancement methods and some existing similar methods.
2) Automatic fuzzy segmentation for infrared vehicle target based on genetic algorithm. According to the characteristic of infrared images, a new auto(?)atic fuzzy segmentation method is presented based on genetic algorithm to segment vehicle target from an infrared image. Firstly, a region of interest (ROI) is selected in order to reduce computation cost. Secondly, the ROI is enhanced by fuzzy algorithm. Thirdly, 2D Maximum Between-cluster Variance algorithm is applied to segment the ROI. At the same time, the genetic algorithm is combined with 2D MBV to make the calculation faster by its capacity of searching the best answer in a threshold space. Then we detect fuzzy edge based on shortening width of fuzzy edge. The final segmentation image can be obtained by OR and filling operations for the segmented region by combining 2D MBV with fuzzy edge. Exper(?)mental results show that the new method can get higher well and truly vehicle target than 1D OTSU or 2D OTSU.
3) Infrared vehicle target recognition based on RBF network. A vehicle recognition approach is proposed based on radial basis function (RBF) neural Network. It extracts the invariant features for translation, rotation, and scale change of vehicle targets: 8 discrete cosine transformation descriptors, 6 independent invariant moments and 3 region characterizations. Compared with BP network, the RBF Network is faster and has higher recognition rate.
引文
[1]荆文芳.飞机红外图像的检测识别与跟踪技术研究[D].西北工业大学博士论文,2006.
[2]姜锦锋.红外图像的目标检测识别与跟踪技术研究[D].西北工业大学硕士论文,2004.
[3]Ronald G.Driggers,Richard Vollmerhausen,Keith Krapels.Target identification performance as a function of temporal and fixed pattern noise.Society of photo-Optical instrumentation engineers,2001,40(3),443-447.
[4]Masataka Kagesawa,Shinichi Ueno,Katsushi Ikeuchi.Recognizing vehicles in infrared images using IMAP parallel vision board.IEEE Trans.On intelligent transportation systems,2001,2(1),10-17.
[5]张燕妮,娄树理.红外图像模式识别的预处理[J].兵工自动化,2005(9):42-49.
[6]邵凡麒.红外图像处理[D].南京理工大学硕士论文,2005.
[7]管慧娟.基于区域的图像分割方法[D].大连理工大学硕士论文,2005.
[8]Xinfu Li,J iaomin Liu.Edge Detection on Arc Image of Low Voltage Apparatus[C].IEEE Proceedings of the Second International Conference on Machine Learning and Cybernetics,Xipan,2003,2921-2924.
[9]夏勇:图像分割技术研究[D].西北工业大学硕士论文.2004.
[10]韩建栋,向健勇等.一种基于小波的图像模糊熵阈值分割算法[J].红外技术.2004.26(3):29-32.
[11]王迅,周建忠,欧阳艺.海上目标红外特征的选取方法研究[J].光电技术应用,2004,19(3):1-3.
[12]罗笑冰,黎湘.基于特征不变量的红外图像识别研究[J].系统工程与电子技术,2004,26(4):539-541
[13]Sun-Gu Sun,Hyun Park.Wook invariant feature extraction based on radial and distance function for automatic target recognition.International Conference on Image Process,2002:345-348.
[14]Jessica L,Herman Ensign.Target identification algorithm for the ANAAS 44V forward looking infrared.United States Navy B.S.Standford University,June 2000:1-65.
[15]HUANC Yon-jie,CHEN Dong,LIU Jun-yi.Target feature extraction method of infrared image[J].Infrared and L user Engineering.2002,31(5):387-394.
[16]刘松涛,沈同圣,周晓东,韩艳丽.红外成像型制导系统舰船目标实时识别技术研究[J].红外与毫米波学报.2004,23(1):43-46.
[17]罗军,杨卫平,沈振康.红外图像中机场跑道的自动目标识别[J].红外技术,2003,25(3):13-17.
[18]M.Liang,M.J.Palakal.Airbome sonar target recognition using artificial neural network[J]Mathematical and computer modeling,2002,35:429-440.
[19]李秋华,李吉成等.基于模糊综合的红外目标融合识别[J].国防科技大学学报,2003,25(1):51-55.
[20]Lipchen Alex Chan,Sandor Z.Der,Nasser M.Nasrabadi.Dualband FLIR for automatic target recognition[J].Information fusion,2003,4:35-45.
[21]Engin Avci,Ibrahim Turkoglu,Mustafa Poyraz.Intelligent target recognition based on wavelet pack neural network[J].Expert systems with applications,2005,29:175-182.
[22]Zehang Sun,George Bebis,Ronald Miller.Object detection using feature subset selection[J].Pattern Recognition,2004,37:2165-2176.
[23]姜锦锋.红外图像目标检测、识别及跟踪技术研究[D].西北工业大学硕士论文.2004.
[24]Gonzalez,Rafael C.等.Digital image processing.[M].Beijing:Publishing House of Electronics Industry;Pearson Education,2002.
[25]舒金龙,于振红等.一种改进的红外图像模糊增强方法[J].系统工程与电子技术,2005,27(6):957-959.
[26]吴盘龙,李言俊,张科.一种红外目标图像的自动分割方法[J],计算机工程,2006,32(11):32-34.
[27]周激流 吕航.一种基于新型遗传算法的图像自适应增强算法的研究[J].计算机学报,2001,24(9):959-964.
[28]周明,孙树栋编著.遗传算法原理及应用[M].北京:国防工业出版社,1999.
[29]王小平,曹立明,遗传算法--理论(?)应用与软件实现[M]西安:西安交通大学出版社,2002.
[30]胡硕,基于遗传算法的图像分割研究(?)东北师范大学硕士学位论文,2003.
[31]Zensho Nakao,Yen-Wei Chen,E(?)ary reconstruction of gray images,Proceedings of IEEE International Conference on(?)tionary Computation 1996:458-462.
[32]Trent Bills,Ashok Samal,Two dime(?)chromosomes and their application to computer vision,SPIE Neural and Stochastic Me(?)Image and Signal Processing Ⅲ,2304:65-75.
[33]魏晗,张长江,胡敏等.基于遗传算法的图像(?)应模糊增强[J].光电子。激光.已录用
[34]金梅,张长江.一种有效的红外图像中人造目标分割方法[J].光电工程,2005,32(4):82-85.
[35]Ramar K,ArumugamS,SivanandmSN.Enha(?)ement of noisy and blurred image:a fuzzy operator approach[J].Advances in Modeling and Analysis,1999,42(1):49-60.
[36]Cheng HV,Xu H.A novel fuzzy logic approach to contrast enhancement[J].Pattern Recognition,2000,33(5):809-819.
[37]Farzam F,Bagher M.Modified iterative fuzzy con(?)ol based filter for image enhancement with multiplicative noise removal property[A].ln:ICF[C],Paris,2001:539-544.
[38]孙即祥 编著.图像分析[M].北京:科学出版社,2004.
[39]KUNDU M K,PAL S K.Automatic Selection of Object Enhancement Operator with Quantitative Justification Based on Fuzzy Set Theoret(?)Measures[J].Pattern Recognition Letters,1990,11(12):811-829.
[40]PALSK,GHOSHA.Fuzzy Geometry in Image Analysis[J].Fuzzy Sets and Systems,1992,48(1):23-40.
[41]熊兴华,钱曾波等.基于遗传优化的分段线性影像增强[J].测绘学报,2004,33(4):341-346.
[42]Tubbs J D.A note on parametric image enhancement[J].Pattern Recognition,1987,30(6):617-621.
[43]张长江,付梦印等.基于模拟退火算法的红外图像自适应对比度增强[J].中国图象图形学报,2004,9(4):391-395.
[44]LEUJG.Image Contrast Enhancement Based on the Intensities of Edge Pixels.[J].CVGIP:Graphical Models and Image Processing,1992,54(6):497-506.
[45]工春柏,赵保军,何佩棍.基于免疫遗传算法的自适应图像分割方法[J].红外与激光工程,2004,33(2):178-193.
[46]陈小梅,倪国强,刘明奇.基于分水岭算法的红外图像分割方法[J].光电子·激光,2001,12(10):1072-1075.
[47]Wenbing Tao,Hai Jin and Liman Liu.Object segmentation using ant colony optimization algorithm and fuzzy entropy[J].Pattern Recognition Letters,2007,28(7):788-796.
[48]杜晓晨,刘建平.基于二维OTSU和遗传算法的红外图像分割方法[J],红外技术,2005,27(1):66-69.
[49]吴盘龙,李言俊,张科.一种红外目标图像的自动分割方法[J],计算机工程,2006,32(11):32-34.
[50]魏晗,张长江.基于遗传算法的红外车辆目标自动模糊分割[J].已投光电工程
[51]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999.
[52]张爱华,余胜生,周敬利.一种二维直方图阈值化图像分割的后处理方法[J].华中技大学学报(自然科学版),2002,30(10):59-61.
[53]李红松,候朝桢.一种新的模糊边缘检测算法[J].计算机工程,2003,29(9):1-2.
[54]Gonzalez,Rafael C.Digital image processing using MATLAB.Beijing:Pub.House of Electronics Industry:Pearson Education(Asia)Co.,2004.
[55]林通,石青云.一种基于边缘生长的灰度利彩色图象分割方法[J].中国图象图形学报,2000,5(11):911-915.
[56]王璞,董慧颖.车牌字符识别的混合特征提取方法[J].沈阳工业学院学报.2003.22(1):30-33.
[57]冯春环,涂建平等.基于离散余弦变换的红外目标识别算法[J].系统仿真学报.2005.17(6):1363-1365.
[58]许东,吴铮.基于MATLAB6.x的系统分析与设计-神经网络[M].西安:西安电子科技大学 出版社,2002.
[59]毛建旭,王耀南.径向基函数神经网络的遥感图象分类[J].系统仿真学报增刊,2001.
[60]Jamuna Kanta Sing,Dipak Kumar Basu,Mita Nasipurietal.Face recognition using point symmetry distance-based RBF network[J].Applied Soft Computing.2007,7(1):58-70.
[2]姜锦锋.红外图像的目标检测识别与跟踪技术研究[D].西北工业大学硕士论文,2004.
[3]Ronald G.Driggers,Richard Vollmerhausen,Keith Krapels.Target identification performance as a function of temporal and fixed pattern noise.Society of photo-Optical instrumentation engineers,2001,40(3),443-447.
[4]Masataka Kagesawa,Shinichi Ueno,Katsushi Ikeuchi.Recognizing vehicles in infrared images using IMAP parallel vision board.IEEE Trans.On intelligent transportation systems,2001,2(1),10-17.
[5]张燕妮,娄树理.红外图像模式识别的预处理[J].兵工自动化,2005(9):42-49.
[6]邵凡麒.红外图像处理[D].南京理工大学硕士论文,2005.
[7]管慧娟.基于区域的图像分割方法[D].大连理工大学硕士论文,2005.
[8]Xinfu Li,J iaomin Liu.Edge Detection on Arc Image of Low Voltage Apparatus[C].IEEE Proceedings of the Second International Conference on Machine Learning and Cybernetics,Xipan,2003,2921-2924.
[9]夏勇:图像分割技术研究[D].西北工业大学硕士论文.2004.
[10]韩建栋,向健勇等.一种基于小波的图像模糊熵阈值分割算法[J].红外技术.2004.26(3):29-32.
[11]王迅,周建忠,欧阳艺.海上目标红外特征的选取方法研究[J].光电技术应用,2004,19(3):1-3.
[12]罗笑冰,黎湘.基于特征不变量的红外图像识别研究[J].系统工程与电子技术,2004,26(4):539-541
[13]Sun-Gu Sun,Hyun Park.Wook invariant feature extraction based on radial and distance function for automatic target recognition.International Conference on Image Process,2002:345-348.
[14]Jessica L,Herman Ensign.Target identification algorithm for the ANAAS 44V forward looking infrared.United States Navy B.S.Standford University,June 2000:1-65.
[15]HUANC Yon-jie,CHEN Dong,LIU Jun-yi.Target feature extraction method of infrared image[J].Infrared and L user Engineering.2002,31(5):387-394.
[16]刘松涛,沈同圣,周晓东,韩艳丽.红外成像型制导系统舰船目标实时识别技术研究[J].红外与毫米波学报.2004,23(1):43-46.
[17]罗军,杨卫平,沈振康.红外图像中机场跑道的自动目标识别[J].红外技术,2003,25(3):13-17.
[18]M.Liang,M.J.Palakal.Airbome sonar target recognition using artificial neural network[J]Mathematical and computer modeling,2002,35:429-440.
[19]李秋华,李吉成等.基于模糊综合的红外目标融合识别[J].国防科技大学学报,2003,25(1):51-55.
[20]Lipchen Alex Chan,Sandor Z.Der,Nasser M.Nasrabadi.Dualband FLIR for automatic target recognition[J].Information fusion,2003,4:35-45.
[21]Engin Avci,Ibrahim Turkoglu,Mustafa Poyraz.Intelligent target recognition based on wavelet pack neural network[J].Expert systems with applications,2005,29:175-182.
[22]Zehang Sun,George Bebis,Ronald Miller.Object detection using feature subset selection[J].Pattern Recognition,2004,37:2165-2176.
[23]姜锦锋.红外图像目标检测、识别及跟踪技术研究[D].西北工业大学硕士论文.2004.
[24]Gonzalez,Rafael C.等.Digital image processing.[M].Beijing:Publishing House of Electronics Industry;Pearson Education,2002.
[25]舒金龙,于振红等.一种改进的红外图像模糊增强方法[J].系统工程与电子技术,2005,27(6):957-959.
[26]吴盘龙,李言俊,张科.一种红外目标图像的自动分割方法[J],计算机工程,2006,32(11):32-34.
[27]周激流 吕航.一种基于新型遗传算法的图像自适应增强算法的研究[J].计算机学报,2001,24(9):959-964.
[28]周明,孙树栋编著.遗传算法原理及应用[M].北京:国防工业出版社,1999.
[29]王小平,曹立明,遗传算法--理论(?)应用与软件实现[M]西安:西安交通大学出版社,2002.
[30]胡硕,基于遗传算法的图像分割研究(?)东北师范大学硕士学位论文,2003.
[31]Zensho Nakao,Yen-Wei Chen,E(?)ary reconstruction of gray images,Proceedings of IEEE International Conference on(?)tionary Computation 1996:458-462.
[32]Trent Bills,Ashok Samal,Two dime(?)chromosomes and their application to computer vision,SPIE Neural and Stochastic Me(?)Image and Signal Processing Ⅲ,2304:65-75.
[33]魏晗,张长江,胡敏等.基于遗传算法的图像(?)应模糊增强[J].光电子。激光.已录用
[34]金梅,张长江.一种有效的红外图像中人造目标分割方法[J].光电工程,2005,32(4):82-85.
[35]Ramar K,ArumugamS,SivanandmSN.Enha(?)ement of noisy and blurred image:a fuzzy operator approach[J].Advances in Modeling and Analysis,1999,42(1):49-60.
[36]Cheng HV,Xu H.A novel fuzzy logic approach to contrast enhancement[J].Pattern Recognition,2000,33(5):809-819.
[37]Farzam F,Bagher M.Modified iterative fuzzy con(?)ol based filter for image enhancement with multiplicative noise removal property[A].ln:ICF[C],Paris,2001:539-544.
[38]孙即祥 编著.图像分析[M].北京:科学出版社,2004.
[39]KUNDU M K,PAL S K.Automatic Selection of Object Enhancement Operator with Quantitative Justification Based on Fuzzy Set Theoret(?)Measures[J].Pattern Recognition Letters,1990,11(12):811-829.
[40]PALSK,GHOSHA.Fuzzy Geometry in Image Analysis[J].Fuzzy Sets and Systems,1992,48(1):23-40.
[41]熊兴华,钱曾波等.基于遗传优化的分段线性影像增强[J].测绘学报,2004,33(4):341-346.
[42]Tubbs J D.A note on parametric image enhancement[J].Pattern Recognition,1987,30(6):617-621.
[43]张长江,付梦印等.基于模拟退火算法的红外图像自适应对比度增强[J].中国图象图形学报,2004,9(4):391-395.
[44]LEUJG.Image Contrast Enhancement Based on the Intensities of Edge Pixels.[J].CVGIP:Graphical Models and Image Processing,1992,54(6):497-506.
[45]工春柏,赵保军,何佩棍.基于免疫遗传算法的自适应图像分割方法[J].红外与激光工程,2004,33(2):178-193.
[46]陈小梅,倪国强,刘明奇.基于分水岭算法的红外图像分割方法[J].光电子·激光,2001,12(10):1072-1075.
[47]Wenbing Tao,Hai Jin and Liman Liu.Object segmentation using ant colony optimization algorithm and fuzzy entropy[J].Pattern Recognition Letters,2007,28(7):788-796.
[48]杜晓晨,刘建平.基于二维OTSU和遗传算法的红外图像分割方法[J],红外技术,2005,27(1):66-69.
[49]吴盘龙,李言俊,张科.一种红外目标图像的自动分割方法[J],计算机工程,2006,32(11):32-34.
[50]魏晗,张长江.基于遗传算法的红外车辆目标自动模糊分割[J].已投光电工程
[51]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999.
[52]张爱华,余胜生,周敬利.一种二维直方图阈值化图像分割的后处理方法[J].华中技大学学报(自然科学版),2002,30(10):59-61.
[53]李红松,候朝桢.一种新的模糊边缘检测算法[J].计算机工程,2003,29(9):1-2.
[54]Gonzalez,Rafael C.Digital image processing using MATLAB.Beijing:Pub.House of Electronics Industry:Pearson Education(Asia)Co.,2004.
[55]林通,石青云.一种基于边缘生长的灰度利彩色图象分割方法[J].中国图象图形学报,2000,5(11):911-915.
[56]王璞,董慧颖.车牌字符识别的混合特征提取方法[J].沈阳工业学院学报.2003.22(1):30-33.
[57]冯春环,涂建平等.基于离散余弦变换的红外目标识别算法[J].系统仿真学报.2005.17(6):1363-1365.
[58]许东,吴铮.基于MATLAB6.x的系统分析与设计-神经网络[M].西安:西安电子科技大学 出版社,2002.
[59]毛建旭,王耀南.径向基函数神经网络的遥感图象分类[J].系统仿真学报增刊,2001.
[60]Jamuna Kanta Sing,Dipak Kumar Basu,Mita Nasipurietal.Face recognition using point symmetry distance-based RBF network[J].Applied Soft Computing.2007,7(1):58-70.