智能交通ⅹ图像阈值分割方法研究
|
摘要
随着汽车拥有量急剧上涨,智能交通成为一个新兴的研究方向。图像处理技术是智能交通系统的重要前沿研究领域,具有十分重要的理论意义和应用价值。本文主要研究对车牌图像、车辆图像及道路图像的阈值分割技术。
本文首先对智能交通技术作了概述,对图像阈值分割的一般方法进行综述,指出了现有算法存在的不足,相应地提出了新的算法。
二维Shannon信息熵法是图像阈值分割中常用的经典算法,但存在着不足。为此,提出了二维指数信息熵阈值选取方法,克服了对数熵的不足,提高了速度。同时给出其快速算法,将二维阈值转化为一维。结果表明,该算法能快速准确地实现图像分割。
最小类内方差法(Otsu法)分割精确,应用范围广泛,实质上是最小二乘法(L2范数)。本文提出了基于最小类内绝对差(L1范数)及最大差(L∞范数)的阈值分割算法,导出了这两种算法的二维算法。通过比较,发现这两种方法在某些类型图像下,阈值分割效果明显优于最小类内方差法,其二维算法的分割效果普遍优于相应的一维算法。
基于熵的阈值选取方法是一类颇受关注的阈值分割算法。本文提出了二维Renyi熵的阈值分割两种不同的快速递推算法,都可以将计算复杂性由O(L4)减少为O(L2)。实验表明,二维Renyi熵阈值选取算法分割准确,这两种快速算法的运行时间不到原算法的0.1%。
本文在指出现有二维直方图区域直分法中存在明显错分的基础上,提出二维直方图区域斜分法,导出了二维直方图斜分的Otsu阈值选取公式及快速递推算法。结果表明,二维直方图斜分可使分割后的图像内部区域均匀,边界形状准确,更具有稳健的抗噪性,运算速度大大提高。
最后,本文将群智能中的人工鱼群算法应用到图像阈值分割算法中,提出了二维Otsu阈值分割的人工鱼群算法。通过与基于基本遗传算法及最优保存策略遗传算法进行比较,发现人工鱼群算法能够准确找到最佳阈值,收敛速度更快。
With the increase of vihecles, the intelligent traffic becomes to a new research direction. Applying image processing technology to intelligent traffic system is a challenging field which has great theoretical significance and practical value. This paper concerns on the thresholding segmentation on the images of licese plate, vihecle and road.
Firstly, the intelligent traffic techinology is introduced. On the basis of reviewing the method of image thresholding segmemntation, we point out the shortages of the existing algorithms and propose several new algorithms.
The two-dimensional Shannon’s information entropy is a classical and commonly used image segmentation method, but there are still some disadvantages involved. Then, a two-dimensional exponent information entropy for threshold selection is proposed here, which could overcome the disadvantages in the Shannon’s entropy. Meaanwhile, a fast algorithm of two-dimensional exponent entropy thresholding method is also given, which changed the two-dimensional threshold into one-dimensional. The results of the experiment indicate that the proposed algorithm has high speed of calculation and good segmentation quality.
The Minimum Within-Cluster Variance algorithm (Otsu) has a good segmentation quality and wide suitable scope, which is actually the Least-Squares algorithm (L2-Norm). Two algorithm for thresholding are proposed in this paper, which are based on Minimum Within-Cluster Absolute Difference (L1-Norm) and Minimum Within-Cluster Maximum Difference (L∞-Norm). And the corresponding two-dimensional algorithms of those two new methods are also presented. The results show that those two new methods have much better perfoemance for some kinds of images, and each of the two-dimensional algorithms is better than its own one-dimensional algorithm.
Thresholding algorithm based on entropy is one of the most famous methods. In this paper, two fast recurring two-dimensional Renyi entropic thresholding algorithms, whose computational complexities are both only O(L2), are proposed, while the computational complexity of the original algorithm is O(L4). Experimental results show that these two recurring algorithms can both greatly reduce the processing time of images, which is less than 0.1% of the original algorithm.
Baed on the obvious wrong segmentation in the existing two-dimensional histogram vertical segmentation method, a two-dimensional histogram oblique segmentation method is proposed. Then the formula and its fast recursive algorithm of the maximum Shannon entropy thresholding are deduced based on the two-dimensional histogram oblique segmentation. Experimental results show that the proposed method makes the inner part uniform and the edge accurate in the threshold image, and it has a better anti-noise property with the increase of its speed.
In this paper, the fish-swarm algorithm of swarm intelligence is also introduced in image thresholding, and the two-dimensional Otsu thresholding algorithm baes on the fish-swarm algorithm is proposed. Comparition with single genetic algorithm and the elitist strategy genetic algorithm shows that this algorithm could select the best threshold accurately with a faster convergent speed.
本文首先对智能交通技术作了概述,对图像阈值分割的一般方法进行综述,指出了现有算法存在的不足,相应地提出了新的算法。
二维Shannon信息熵法是图像阈值分割中常用的经典算法,但存在着不足。为此,提出了二维指数信息熵阈值选取方法,克服了对数熵的不足,提高了速度。同时给出其快速算法,将二维阈值转化为一维。结果表明,该算法能快速准确地实现图像分割。
最小类内方差法(Otsu法)分割精确,应用范围广泛,实质上是最小二乘法(L2范数)。本文提出了基于最小类内绝对差(L1范数)及最大差(L∞范数)的阈值分割算法,导出了这两种算法的二维算法。通过比较,发现这两种方法在某些类型图像下,阈值分割效果明显优于最小类内方差法,其二维算法的分割效果普遍优于相应的一维算法。
基于熵的阈值选取方法是一类颇受关注的阈值分割算法。本文提出了二维Renyi熵的阈值分割两种不同的快速递推算法,都可以将计算复杂性由O(L4)减少为O(L2)。实验表明,二维Renyi熵阈值选取算法分割准确,这两种快速算法的运行时间不到原算法的0.1%。
本文在指出现有二维直方图区域直分法中存在明显错分的基础上,提出二维直方图区域斜分法,导出了二维直方图斜分的Otsu阈值选取公式及快速递推算法。结果表明,二维直方图斜分可使分割后的图像内部区域均匀,边界形状准确,更具有稳健的抗噪性,运算速度大大提高。
最后,本文将群智能中的人工鱼群算法应用到图像阈值分割算法中,提出了二维Otsu阈值分割的人工鱼群算法。通过与基于基本遗传算法及最优保存策略遗传算法进行比较,发现人工鱼群算法能够准确找到最佳阈值,收敛速度更快。
With the increase of vihecles, the intelligent traffic becomes to a new research direction. Applying image processing technology to intelligent traffic system is a challenging field which has great theoretical significance and practical value. This paper concerns on the thresholding segmentation on the images of licese plate, vihecle and road.
Firstly, the intelligent traffic techinology is introduced. On the basis of reviewing the method of image thresholding segmemntation, we point out the shortages of the existing algorithms and propose several new algorithms.
The two-dimensional Shannon’s information entropy is a classical and commonly used image segmentation method, but there are still some disadvantages involved. Then, a two-dimensional exponent information entropy for threshold selection is proposed here, which could overcome the disadvantages in the Shannon’s entropy. Meaanwhile, a fast algorithm of two-dimensional exponent entropy thresholding method is also given, which changed the two-dimensional threshold into one-dimensional. The results of the experiment indicate that the proposed algorithm has high speed of calculation and good segmentation quality.
The Minimum Within-Cluster Variance algorithm (Otsu) has a good segmentation quality and wide suitable scope, which is actually the Least-Squares algorithm (L2-Norm). Two algorithm for thresholding are proposed in this paper, which are based on Minimum Within-Cluster Absolute Difference (L1-Norm) and Minimum Within-Cluster Maximum Difference (L∞-Norm). And the corresponding two-dimensional algorithms of those two new methods are also presented. The results show that those two new methods have much better perfoemance for some kinds of images, and each of the two-dimensional algorithms is better than its own one-dimensional algorithm.
Thresholding algorithm based on entropy is one of the most famous methods. In this paper, two fast recurring two-dimensional Renyi entropic thresholding algorithms, whose computational complexities are both only O(L2), are proposed, while the computational complexity of the original algorithm is O(L4). Experimental results show that these two recurring algorithms can both greatly reduce the processing time of images, which is less than 0.1% of the original algorithm.
Baed on the obvious wrong segmentation in the existing two-dimensional histogram vertical segmentation method, a two-dimensional histogram oblique segmentation method is proposed. Then the formula and its fast recursive algorithm of the maximum Shannon entropy thresholding are deduced based on the two-dimensional histogram oblique segmentation. Experimental results show that the proposed method makes the inner part uniform and the edge accurate in the threshold image, and it has a better anti-noise property with the increase of its speed.
In this paper, the fish-swarm algorithm of swarm intelligence is also introduced in image thresholding, and the two-dimensional Otsu thresholding algorithm baes on the fish-swarm algorithm is proposed. Comparition with single genetic algorithm and the elitist strategy genetic algorithm shows that this algorithm could select the best threshold accurately with a faster convergent speed.
引文
[1]王笑晶.中国职能交通系统发展战略研究[J].交通运输系统与信息, 2006, 6(4): 9~13.
[2]国家智能交通系统工程技术研究中心.中国智能交通系统文集[M].北京:中国铁道出版社, 2005年.
[3]陆化普,李瑞敏.智能交通系统概论[M].北京:中国铁道出版社, 2004.
[4] Gerland H. ITS intelligent transportation system: fleet management with GPS dead reckoning, advanced displays, smartcards, etc[C]. IEEE-IEE Vehicle Navigation & Information Systems Conference, Ottawa, Canada, 1993, 606~611.
[5] White C. Intelligent transportation systems: Integrating information technology and the surface transportation system[C]. 1995 IEEE ICSMC, Vancouver, British Columbia, 1995, 4000~4003.
[6] Braun A. Intelligent transportation systems: mirage or reality[J]. Microware Journal, 1997, 40(8): 22~28.
[7] Maier M. On architecting and intelligent transport systems[J]. IEEE Transactions, AES, 1997, 33(2): 610~625.
[8]郁梅,蒋刚毅,郁伯康.智能交通系统中的计算机视觉技术应用[J].计算机工程与应用, 2001, 10: 101~103.
[9]王国良.图像处理技术在智能交通系统中应用的研究[D].大连海事大学,博士学位论文, 2007年.
[10]杨明,陆建业,王宏,等.基于视觉的道路跟踪[J].模式识别与人工智能, 2001, 14(2): 186~193.
[11]邱巍.基于视觉的全天候驾驶员疲劳与精神分散状态检测方法研究[D].吉林大学,博士学位论文, 2010年.
[12]管欣,贾鑫,高振海.基于道路图像对比度——区域均匀性图分析的自适应阈值算法[J].吉林大学学报(工学版), 2008, 4: 758~763.
[13]梁海文,张文革.视觉导航中的图像分割算法研究[J].铸造技术, 2009, 5: 682~685.
[14]刘新宇,吴勇,李龙.道路标线图像分割方法研究[J].交通与计算机, 2008, 6: 56~60.
[15] Redmill K, Upadhya S, Krishnamurthy A et al. A lane tracking system for intelligent vehicle application[C]. Proceedings of the IEEE Intelligent Transportation Systems, 2001, 273~279.
[16]毕胜.人体行为视觉识别中分割方法的研究[D].大连海事大学,博士学位论文, 2007年.
[17]崔海花.高速公路交通事件检测系统研究[D].长安大学,硕士学位论文, 2007年.
[18] Lu S. Using multiple cues for hand tracking and model refinement[C]. In Computer Vision andPattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference 2003.
[19]富煜清,沈巍,黄心晔.汽车牌照的提取方法研究[J].模式识别与人工智能, 2000, 13(3): 345~ 348.
[20]李刚,宋文静.基于图像直方图的车牌图像二值化方法研究[J].交通运输系统工程与信息, 2009, 1: 113~116.
[21]左奇,史忠科.一种基于数学形态学的实时车牌图像分割方法[J].中国图象图形学报, 2003, 8(3): 281~285.
[22] Kim S, Kim D, Ryu Y, Kim G. A robust license-plate extraction method under complex image conditions[C]. 16th ICPR, Quebec, Canada, 2002, 216~219.
[23]董立菊.图像阈值化技术的综述、分类及评价[J].沈阳大学学报,2004,16(4):8~11.
[24]王鹏伟.基于多尺度理论的图像分割方法研究[D].中国科学技术大学,博士学位论文, 2007年.
[25]杨修国.图像阈值分割方法研究与分析[D].华东师范大学,硕士学位论文, 2009年.
[26]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(一)[J].数据采集与处理, 1993, 8 (3) :193~201.
[27]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(二)[J].数据采集与处理, 1993, 8 (4) : 268~277.
[28] Ostu N. A threshold selection method from gray-level histogram[J]. IEEE Transactions, SMC, 1979,9(1):62~66.
[29]刘健庄,栗文青.灰度图像的二维Otsu自动阈值分割法[J].自动化学报, 1993,19(1):101~105.
[30] Gong J, Li L, Chen W. Fast recursive algorithms for two-dimensional thresholding[J]. Pattern Recognition,1998,31(3): 295~300.
[31]李鉴庆,左坤隆.图像阈值选取的一种快速算法[J].计算机与现代化, 2001, 76(6): 11~14.
[32]梁光明,刘东华,李波,等.二维Otsu自适应阈值分割算法的改进[J].自动化技术与应用, 2002, 21(5): 43~47.
[33]郝颖明,朱枫. 2维Otsu自适应阈值的快速算法[J].中国图象图形学报, 2005, 10(4): 484~488.
[34] Kapur J, Sahoo P, Wong A.A new method for grey-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics and Image Processing, 1985,29: 273~ 285.
[35] Abutaleb A. Automatic thresholding of gray-level picture using two-dimensional entropies[J]. Pattern Recognition, 1989, 47(1): 22~32.
[36]刘健庄.基于二维熵的图像阈值选择快速算法[J].模式识别和人工智能, 1991, 4(3): 46~53.
[37] Chen W, Wen C, Yang C. A fast two-dimensional entropic thresholding algorithm[J]. Pattern Recognition, 1994, 27(7): 885~893.
[38]龚坚,李立源,陈维南.二维熵阈值分割的快速算法[J].东南大学学报, 1996, 26(4): 31~36.
[39]张毅军,吴雪菁,夏良正.二维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.
[40]刘京南,陈从颜,余玲玲,等.一种快速二维熵阈值分割算法[J].计算机应用研究, 2002, (1):67~ 70.
[41] Li C, Lee C. Minimum cross entropy thresholding[J]. Pattern Recognition, 1993, 26: 617~625.
[42] Chang C, Chen K, Wang J et al. A relative entropy-based approach to image thresholding[J]. Pattern Recognition,1994,27(9):1275~1289.
[43] Li C, Tam P. An iterative algorithm for minimum cross entropy thresholding[J]. Pattern Recognition Letters, 1998, 19(8): 771~776.
[44]薛景浩,章毓晋,林行刚.基于最大类间后验交叉熵的阈值化分割算法[J].中国图像图形学报, 1999, 4(2): 110~114.
[45] Sahoo P, Wilkins C, Yeage J. Threshold selection using Renyi’s entropy[J]. Pattern Recognition. 1997, 30(1): 71~84.
[46] Sahoo P, Arora G. A thresholding method based on two-dimensional Renyi’s entropy[J]. Pattern Recognition, 2004, 37(6): 1149~1161.
[47] Sahoo P, Arora G. Image thresholding using two-dimensional Tsallis-Havrada- Charvat entropy[J]. Pattern Recognition Letters, 2006, 27(6): 520~528.
[48]黄金杰,郭鲁强,逯仁虎,等.改进的二维Renyi熵图像阈值分割[J].计算机科学, 2010, 37(10): 251~253.
[49]卓问,曹治国,肖阳.基于二维Arimoto熵的阈值分割方法[J].模式识别与人工智能, 2009, 22(2): 208~213.
[50] Bezdek J. Pattern recognition with fuzzy objective function algorithms[M]. New York: Plenum, 1981.
[51]丁震,胡钟山,杨静宇,等.一种基于模糊聚类的快速二值化方法[J].计算机学报, 1998, 20(增刊): 331~334.
[52]匡泰,朱清新,孙跃. FCM算法用于灰度图像分割的初始化方法的研究[J].计算机应用, 2006, 26(4): 784~786.
[53] Yin P. A fast scheme for optimal thresholding using genetic algorithm[J]. Signal Processing, 1999,72(2): 85~95.
[54]曾伟,袁宝峰,朱桂斌.基于模糊最大类间方差的图像阈值分割算法[J].计算机应用, 2008, 6:22~ 24.
[55]郭海涛,王连玉,田坦,等.基于二维属性直方图和遗传算法的图像阈值化[C]. 2005年信息与通信领域博士后学术论文集, 2005年.
[56] Shen T, Fang Z, Wu L et al. A new adaptive image segmentation method[J]. Journal of Beijing Institute of Technology, 1998, 7(3): 316~321.
[57] Wang L, Shen T. Two-dimensional entropy method based on genetic algorithm[J]. Journal of Beijing Institute of Techology, 2002, 11(2): 184~188.
[58]梅蓉,姜长生,陈谋.基于遗传算法的二维最小交叉熵的动态图像分割[J].电光与控制, 2005, 12(1): 30~34.
[59] Chun D, Yang H. Robust image segmentation using genetic algorithm with a fuzzy measure[J]. Pattern Recognition, 1996, 29(7): 1195~1211.
[60]郭英凯,杨杰,陆正刚.基于模糊和遗传算法的阈值分割方法[J].红外与激光工程, 2000, 29(5): 15~18.
[61] Tao W, Tian J, Liu J. Image segmentation by three-level thresholding based on maximum fuzzy entropy and genetic algorithm[J]. Pattern Recognition Letters, 2003, 24(16): 3069~3078.
[62]陈修桥,胡以华,黄友锐.基于二维最大相关准则的图像阈值分割[J].红外与毫米波学报, 2005, 24(5): 397~400.
[63]王洪元,史国栋.人工神经网络技术及其应用[M].中国北京:中国石化出版社, 2002年.
[64]石美红,张军英,张晓滨,等.基于改进型脉冲耦合神经网络的图像二值分割[J].计算机仿真, 2002, 19(4): 42~46.
[65]刘勍,马义德,钱志柏.一种基于交叉熵的改进型PCNN图像自动分割新方法[J].中国图像图形学报, 2005, 10(5): 579~584.
[66]朱程辉,陈昕,王金玲.基于RBF神经网络在图像分割参数估计的应用[J].计算机工程与应用, 2003, 30: 85~87.
[67] Shen D, Horace H. A Hopfield neural network for adaptive image segmentation: an active surface paradigm[J]. Pattern Recognition Letters, 1997,18(1): 37~48.
[68]沈定刚,戚飞虎.基于神经网络的自适应图像分割[J].上海交通大学学报, 1994, 28 (增刊): 39~ 45.
[69]章毓晋.图像分割评价技术分类和比较[J].中国图像图形学报, 1996, 1(2): 151~158.
[70] Graaf C. Task-directed evalution of image segmentation method[C]. Proc, 11th ICPR, 1992, 3: 219~222.
[71] Levine M, Nazif A. Dynamic measurement of computer generated image segmentation[J]. IEEE Transactions, PAMI, 1985, 7(2): 155~164.
[72] Yaanoff W, Bacus J. Scene-segmentation algorithm development using error measure[J]. AQCH,1984, 6(1): 45~58.
[73] Strasters K, Gerbrands J. Three-dimensional image segmentation using a split, merge and group approach[J]. Pattern Recognition Letters, 1991, 12(5): 307~325.
[74] Lee S. A comparative performance study of several global thresholding technique for segmentation[J]. CVGIP, 1990, 52(2): 171~190.
[75]李立源,陈维南.一种强鲁棒的完全确定型的快速阈值化方法[J].模式识别与人工智能, 1993, 6: 235~241.
[76] Zhang Y, Gerbrands J. Objective and quantitative segmentation evalution and comparison[J]. Signal Processing, 1994, 39(1-2): 43~54.
[77] Sahoo P. A survey of thresholding techniques[J]. CVGIP, 1988, 41(2): 233~260.
[78] Pun T. A new method for grey-level picture thresholding using the entropy of the histogram[J]. Signal Processing, 1980, 2(3) : 223~237.
[79]潘喆,吴一全.二维指数熵图像阈值选取方法及其快速算法[J].计算机应用, 2007, 27(4): 982~ 985.
[80]吴一全,潘喆.基于最小类内绝对差和最大差的图像阈值分割[J].信号处理, 2008, 24(6): 944~ 946.
[81] Pal N, Pal S. Entropic thresholding[J]. Signal Processing, 1989, 16: 97~108.
[82] Chang C, Wang.J. Vapor cloud detection using relative entropy threshold[C]. SPIE. 2232 : 276~284.
[83] Pal S, Pal N. Object-background classification using a new definition of entropy[C]. Proceedings of IEEE Transactions, SMC, 1988: 773~776.
[84]刘智敏.误差与数据处理[M].北京,原子能出版社, 1981.
[85]程正兴,李水根.数值逼近与常微分方程数值解[M].西安交通大学出版社, 2000年.
[86]林成森.数值分析[M].科学出版社, 2006年.
[87]吴一全,刘冰,王厚枢.液晶显示温度场的数字图像处理[J].数据采集与处理, 1990, 5(3): 23~30
[88]吴一全,郝红杰.二维最大类间离差及其快速分割算法[J].计算机应用研究. 2007, 24(增): 945~946.
[89]潘喆,吴一全.二维Renyi熵图像阈值选取快速递推算法[J].中国体视学与图像分析, 2007, 12(2): 93~97.
[90]吴一全,潘喆.二维Tsallis-Havrda-Charvat熵阈值分割的快速递推算法[J].信号处理, 2009, 25(4): 665~668.
[91]吴一全,潘喆,吴文怡.二维直方图区域斜分阈值分割及快速递推算法[J].通信学报, 2008,29(4): 77~83.
[92]吴一全,潘喆,吴文怡.二维直方图区域斜分最大熵阈值分割算法[J].模式识别和人工智能, 2009, 22(1): 162~168.
[93]吴一全,潘喆,吴文怡.二维直方图斜分Tsallis-Havrda-Charvat熵图像阈值分割[J].光电工程, 2008, 35(7): 53~58.
[94]潘喆,吴一全.二维Otsu图像分割的人工鱼群算法[J].光学学报, 2009, 29(8): 2115~2121.
[95]李晓磊.一种新型的智能优化方法—人工鱼群算法[D].浙江大学,博士学位论文, 2003年.
[96]李晓磊,邵之江,钱积新.一种基于动物自治体的寻优模式:鱼群算法[J].系统工程理论与实践, 2002, 22(11): 32~38.
[97]郭海涛,田坦,王连玉,等.利用二维属性直方图的最大熵的图像分割方法[J].光学学报, 2006, 26(4): 506~509.
[98]陈果,左洪福.图像分割的二维最大熵遗传算法[J].计算机辅助设计与图形学学报, 2002, 14(6): 530~534.
[99]练玉来,耿军雪.遗传算法在二维熵图像分割中的应用[J].现代电子技术, 2004, 182(15): 25~ 27.
[100]常青,王立,邢超,等.基于遗传算法的图像阈值选取[J].计算机工程与应用, 2002, 22: 35~37.
[101]毕惟红,任红民,吴庆标.一种新的遗传算法最优保存策略[J].浙江大学学报(理学版), 2006, 33(1): 32~35.
[2]国家智能交通系统工程技术研究中心.中国智能交通系统文集[M].北京:中国铁道出版社, 2005年.
[3]陆化普,李瑞敏.智能交通系统概论[M].北京:中国铁道出版社, 2004.
[4] Gerland H. ITS intelligent transportation system: fleet management with GPS dead reckoning, advanced displays, smartcards, etc[C]. IEEE-IEE Vehicle Navigation & Information Systems Conference, Ottawa, Canada, 1993, 606~611.
[5] White C. Intelligent transportation systems: Integrating information technology and the surface transportation system[C]. 1995 IEEE ICSMC, Vancouver, British Columbia, 1995, 4000~4003.
[6] Braun A. Intelligent transportation systems: mirage or reality[J]. Microware Journal, 1997, 40(8): 22~28.
[7] Maier M. On architecting and intelligent transport systems[J]. IEEE Transactions, AES, 1997, 33(2): 610~625.
[8]郁梅,蒋刚毅,郁伯康.智能交通系统中的计算机视觉技术应用[J].计算机工程与应用, 2001, 10: 101~103.
[9]王国良.图像处理技术在智能交通系统中应用的研究[D].大连海事大学,博士学位论文, 2007年.
[10]杨明,陆建业,王宏,等.基于视觉的道路跟踪[J].模式识别与人工智能, 2001, 14(2): 186~193.
[11]邱巍.基于视觉的全天候驾驶员疲劳与精神分散状态检测方法研究[D].吉林大学,博士学位论文, 2010年.
[12]管欣,贾鑫,高振海.基于道路图像对比度——区域均匀性图分析的自适应阈值算法[J].吉林大学学报(工学版), 2008, 4: 758~763.
[13]梁海文,张文革.视觉导航中的图像分割算法研究[J].铸造技术, 2009, 5: 682~685.
[14]刘新宇,吴勇,李龙.道路标线图像分割方法研究[J].交通与计算机, 2008, 6: 56~60.
[15] Redmill K, Upadhya S, Krishnamurthy A et al. A lane tracking system for intelligent vehicle application[C]. Proceedings of the IEEE Intelligent Transportation Systems, 2001, 273~279.
[16]毕胜.人体行为视觉识别中分割方法的研究[D].大连海事大学,博士学位论文, 2007年.
[17]崔海花.高速公路交通事件检测系统研究[D].长安大学,硕士学位论文, 2007年.
[18] Lu S. Using multiple cues for hand tracking and model refinement[C]. In Computer Vision andPattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference 2003.
[19]富煜清,沈巍,黄心晔.汽车牌照的提取方法研究[J].模式识别与人工智能, 2000, 13(3): 345~ 348.
[20]李刚,宋文静.基于图像直方图的车牌图像二值化方法研究[J].交通运输系统工程与信息, 2009, 1: 113~116.
[21]左奇,史忠科.一种基于数学形态学的实时车牌图像分割方法[J].中国图象图形学报, 2003, 8(3): 281~285.
[22] Kim S, Kim D, Ryu Y, Kim G. A robust license-plate extraction method under complex image conditions[C]. 16th ICPR, Quebec, Canada, 2002, 216~219.
[23]董立菊.图像阈值化技术的综述、分类及评价[J].沈阳大学学报,2004,16(4):8~11.
[24]王鹏伟.基于多尺度理论的图像分割方法研究[D].中国科学技术大学,博士学位论文, 2007年.
[25]杨修国.图像阈值分割方法研究与分析[D].华东师范大学,硕士学位论文, 2009年.
[26]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(一)[J].数据采集与处理, 1993, 8 (3) :193~201.
[27]吴一全,朱兆达.图像处理中阈值选取方法30年(1962—1992)的进展(二)[J].数据采集与处理, 1993, 8 (4) : 268~277.
[28] Ostu N. A threshold selection method from gray-level histogram[J]. IEEE Transactions, SMC, 1979,9(1):62~66.
[29]刘健庄,栗文青.灰度图像的二维Otsu自动阈值分割法[J].自动化学报, 1993,19(1):101~105.
[30] Gong J, Li L, Chen W. Fast recursive algorithms for two-dimensional thresholding[J]. Pattern Recognition,1998,31(3): 295~300.
[31]李鉴庆,左坤隆.图像阈值选取的一种快速算法[J].计算机与现代化, 2001, 76(6): 11~14.
[32]梁光明,刘东华,李波,等.二维Otsu自适应阈值分割算法的改进[J].自动化技术与应用, 2002, 21(5): 43~47.
[33]郝颖明,朱枫. 2维Otsu自适应阈值的快速算法[J].中国图象图形学报, 2005, 10(4): 484~488.
[34] Kapur J, Sahoo P, Wong A.A new method for grey-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics and Image Processing, 1985,29: 273~ 285.
[35] Abutaleb A. Automatic thresholding of gray-level picture using two-dimensional entropies[J]. Pattern Recognition, 1989, 47(1): 22~32.
[36]刘健庄.基于二维熵的图像阈值选择快速算法[J].模式识别和人工智能, 1991, 4(3): 46~53.
[37] Chen W, Wen C, Yang C. A fast two-dimensional entropic thresholding algorithm[J]. Pattern Recognition, 1994, 27(7): 885~893.
[38]龚坚,李立源,陈维南.二维熵阈值分割的快速算法[J].东南大学学报, 1996, 26(4): 31~36.
[39]张毅军,吴雪菁,夏良正.二维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.
[40]刘京南,陈从颜,余玲玲,等.一种快速二维熵阈值分割算法[J].计算机应用研究, 2002, (1):67~ 70.
[41] Li C, Lee C. Minimum cross entropy thresholding[J]. Pattern Recognition, 1993, 26: 617~625.
[42] Chang C, Chen K, Wang J et al. A relative entropy-based approach to image thresholding[J]. Pattern Recognition,1994,27(9):1275~1289.
[43] Li C, Tam P. An iterative algorithm for minimum cross entropy thresholding[J]. Pattern Recognition Letters, 1998, 19(8): 771~776.
[44]薛景浩,章毓晋,林行刚.基于最大类间后验交叉熵的阈值化分割算法[J].中国图像图形学报, 1999, 4(2): 110~114.
[45] Sahoo P, Wilkins C, Yeage J. Threshold selection using Renyi’s entropy[J]. Pattern Recognition. 1997, 30(1): 71~84.
[46] Sahoo P, Arora G. A thresholding method based on two-dimensional Renyi’s entropy[J]. Pattern Recognition, 2004, 37(6): 1149~1161.
[47] Sahoo P, Arora G. Image thresholding using two-dimensional Tsallis-Havrada- Charvat entropy[J]. Pattern Recognition Letters, 2006, 27(6): 520~528.
[48]黄金杰,郭鲁强,逯仁虎,等.改进的二维Renyi熵图像阈值分割[J].计算机科学, 2010, 37(10): 251~253.
[49]卓问,曹治国,肖阳.基于二维Arimoto熵的阈值分割方法[J].模式识别与人工智能, 2009, 22(2): 208~213.
[50] Bezdek J. Pattern recognition with fuzzy objective function algorithms[M]. New York: Plenum, 1981.
[51]丁震,胡钟山,杨静宇,等.一种基于模糊聚类的快速二值化方法[J].计算机学报, 1998, 20(增刊): 331~334.
[52]匡泰,朱清新,孙跃. FCM算法用于灰度图像分割的初始化方法的研究[J].计算机应用, 2006, 26(4): 784~786.
[53] Yin P. A fast scheme for optimal thresholding using genetic algorithm[J]. Signal Processing, 1999,72(2): 85~95.
[54]曾伟,袁宝峰,朱桂斌.基于模糊最大类间方差的图像阈值分割算法[J].计算机应用, 2008, 6:22~ 24.
[55]郭海涛,王连玉,田坦,等.基于二维属性直方图和遗传算法的图像阈值化[C]. 2005年信息与通信领域博士后学术论文集, 2005年.
[56] Shen T, Fang Z, Wu L et al. A new adaptive image segmentation method[J]. Journal of Beijing Institute of Technology, 1998, 7(3): 316~321.
[57] Wang L, Shen T. Two-dimensional entropy method based on genetic algorithm[J]. Journal of Beijing Institute of Techology, 2002, 11(2): 184~188.
[58]梅蓉,姜长生,陈谋.基于遗传算法的二维最小交叉熵的动态图像分割[J].电光与控制, 2005, 12(1): 30~34.
[59] Chun D, Yang H. Robust image segmentation using genetic algorithm with a fuzzy measure[J]. Pattern Recognition, 1996, 29(7): 1195~1211.
[60]郭英凯,杨杰,陆正刚.基于模糊和遗传算法的阈值分割方法[J].红外与激光工程, 2000, 29(5): 15~18.
[61] Tao W, Tian J, Liu J. Image segmentation by three-level thresholding based on maximum fuzzy entropy and genetic algorithm[J]. Pattern Recognition Letters, 2003, 24(16): 3069~3078.
[62]陈修桥,胡以华,黄友锐.基于二维最大相关准则的图像阈值分割[J].红外与毫米波学报, 2005, 24(5): 397~400.
[63]王洪元,史国栋.人工神经网络技术及其应用[M].中国北京:中国石化出版社, 2002年.
[64]石美红,张军英,张晓滨,等.基于改进型脉冲耦合神经网络的图像二值分割[J].计算机仿真, 2002, 19(4): 42~46.
[65]刘勍,马义德,钱志柏.一种基于交叉熵的改进型PCNN图像自动分割新方法[J].中国图像图形学报, 2005, 10(5): 579~584.
[66]朱程辉,陈昕,王金玲.基于RBF神经网络在图像分割参数估计的应用[J].计算机工程与应用, 2003, 30: 85~87.
[67] Shen D, Horace H. A Hopfield neural network for adaptive image segmentation: an active surface paradigm[J]. Pattern Recognition Letters, 1997,18(1): 37~48.
[68]沈定刚,戚飞虎.基于神经网络的自适应图像分割[J].上海交通大学学报, 1994, 28 (增刊): 39~ 45.
[69]章毓晋.图像分割评价技术分类和比较[J].中国图像图形学报, 1996, 1(2): 151~158.
[70] Graaf C. Task-directed evalution of image segmentation method[C]. Proc, 11th ICPR, 1992, 3: 219~222.
[71] Levine M, Nazif A. Dynamic measurement of computer generated image segmentation[J]. IEEE Transactions, PAMI, 1985, 7(2): 155~164.
[72] Yaanoff W, Bacus J. Scene-segmentation algorithm development using error measure[J]. AQCH,1984, 6(1): 45~58.
[73] Strasters K, Gerbrands J. Three-dimensional image segmentation using a split, merge and group approach[J]. Pattern Recognition Letters, 1991, 12(5): 307~325.
[74] Lee S. A comparative performance study of several global thresholding technique for segmentation[J]. CVGIP, 1990, 52(2): 171~190.
[75]李立源,陈维南.一种强鲁棒的完全确定型的快速阈值化方法[J].模式识别与人工智能, 1993, 6: 235~241.
[76] Zhang Y, Gerbrands J. Objective and quantitative segmentation evalution and comparison[J]. Signal Processing, 1994, 39(1-2): 43~54.
[77] Sahoo P. A survey of thresholding techniques[J]. CVGIP, 1988, 41(2): 233~260.
[78] Pun T. A new method for grey-level picture thresholding using the entropy of the histogram[J]. Signal Processing, 1980, 2(3) : 223~237.
[79]潘喆,吴一全.二维指数熵图像阈值选取方法及其快速算法[J].计算机应用, 2007, 27(4): 982~ 985.
[80]吴一全,潘喆.基于最小类内绝对差和最大差的图像阈值分割[J].信号处理, 2008, 24(6): 944~ 946.
[81] Pal N, Pal S. Entropic thresholding[J]. Signal Processing, 1989, 16: 97~108.
[82] Chang C, Wang.J. Vapor cloud detection using relative entropy threshold[C]. SPIE. 2232 : 276~284.
[83] Pal S, Pal N. Object-background classification using a new definition of entropy[C]. Proceedings of IEEE Transactions, SMC, 1988: 773~776.
[84]刘智敏.误差与数据处理[M].北京,原子能出版社, 1981.
[85]程正兴,李水根.数值逼近与常微分方程数值解[M].西安交通大学出版社, 2000年.
[86]林成森.数值分析[M].科学出版社, 2006年.
[87]吴一全,刘冰,王厚枢.液晶显示温度场的数字图像处理[J].数据采集与处理, 1990, 5(3): 23~30
[88]吴一全,郝红杰.二维最大类间离差及其快速分割算法[J].计算机应用研究. 2007, 24(增): 945~946.
[89]潘喆,吴一全.二维Renyi熵图像阈值选取快速递推算法[J].中国体视学与图像分析, 2007, 12(2): 93~97.
[90]吴一全,潘喆.二维Tsallis-Havrda-Charvat熵阈值分割的快速递推算法[J].信号处理, 2009, 25(4): 665~668.
[91]吴一全,潘喆,吴文怡.二维直方图区域斜分阈值分割及快速递推算法[J].通信学报, 2008,29(4): 77~83.
[92]吴一全,潘喆,吴文怡.二维直方图区域斜分最大熵阈值分割算法[J].模式识别和人工智能, 2009, 22(1): 162~168.
[93]吴一全,潘喆,吴文怡.二维直方图斜分Tsallis-Havrda-Charvat熵图像阈值分割[J].光电工程, 2008, 35(7): 53~58.
[94]潘喆,吴一全.二维Otsu图像分割的人工鱼群算法[J].光学学报, 2009, 29(8): 2115~2121.
[95]李晓磊.一种新型的智能优化方法—人工鱼群算法[D].浙江大学,博士学位论文, 2003年.
[96]李晓磊,邵之江,钱积新.一种基于动物自治体的寻优模式:鱼群算法[J].系统工程理论与实践, 2002, 22(11): 32~38.
[97]郭海涛,田坦,王连玉,等.利用二维属性直方图的最大熵的图像分割方法[J].光学学报, 2006, 26(4): 506~509.
[98]陈果,左洪福.图像分割的二维最大熵遗传算法[J].计算机辅助设计与图形学学报, 2002, 14(6): 530~534.
[99]练玉来,耿军雪.遗传算法在二维熵图像分割中的应用[J].现代电子技术, 2004, 182(15): 25~ 27.
[100]常青,王立,邢超,等.基于遗传算法的图像阈值选取[J].计算机工程与应用, 2002, 22: 35~37.
[101]毕惟红,任红民,吴庆标.一种新的遗传算法最优保存策略[J].浙江大学学报(理学版), 2006, 33(1): 32~35.