遥感图像分割中阈值的自动选取技术研究
|
摘要
在遥感图像的应用中,多数情况下人们往往只对图像中的某些部分感兴趣。为了识别和分析目标,就需要将这些部分从整幅图像中分割出来,并尽量避免背景的干扰及影响。不同的阈值设定方法直接影响到目标提取的精度和图像特征信息的保留程度。传统的通过人机交互确定阈值或者使用经验值的方法主观影响比较大,不能实现自动化提取,并且不能完全保证普遍适用。因此实现遥感图像分割中阈值的自动选取并研究其适用性是一个值得研究的重要内容。
对已有的研究成果分析表明,目前尚没有一种适合于所有图像的通用的阈值自动选取算法。但是,对于具体的图像、具体的需求,的确可以找到效果相当好的自动化阈值选取方法。本文分别对简单图像和复杂图像中阂值的自动选取方法进行了介绍并进行实验。由于后者基于前者,所以本文重点讨论简单图像中的阈值选取方法。
简单遥感图像采用阈值分割时,可使用基于像元灰度的全局阈值法。在保持图像的均匀照度下,对于直方图双峰明显,谷底较深的图像,可采用迭代法；对目标大小适合的图像,可采用最大类间方差法寻找最佳阈值进行图像分割；实时性和稳定性要求高时可选择最小误差法；当图像中目标和背景灰度对比度较低,直方图为单峰,或者目标与背景比例不均衡,目标地物比较小时,可采用最大熵法,但其对噪声点比较敏感；当注重原始图像和分割后图像之间的信息量差异最小时,可采用最小交叉熵阈值法,它在双峰图像和单峰图像中的适用性都很高,但它对目标的大小较敏感。
简单遥感图像中含有噪声,背景灰度不均匀时,可使用基于像元邻域属性的阈值法。本文将一维Otsu算法和一维最大熵算法拓展到二维空间,提出了二维阈值算法；同时还提出一种过渡区加权的算法。这三种方法都能有效地克服噪声的干扰,分割效果总体上都优于一维阈值算法。但从运算时间来看,由于运算量成倍增加,二维算法的计算时间也高于一维算法。
复杂遥感图像中目标灰度层次比较丰富、边界模糊,物体和背景的对比度在图像中各处不一样,可使用局部自适应阈值法。Mean法和Median法对每个像素确定一个以它为中心的窗口,然后求取窗口内的灰度均值和中值作为此像素的阈值,最后移动窗口得到每个像素的阈值。这种方法大大简化了传统阈值差值的算法,并且能兼顾考虑图像各处的具体情况,保证分割效果。
In the application of remote sensing images, people are often interested in specific information of the image. When extracting the specific target information, it is necessary to separate the target from the whole original image and try to avoid the disturbances from the background. How to rationally and effectively obtain the threshold which is used to differentiate the object from the background is the key process. However, thresholds based on different segmentation algorithms would affect the precision of the result and the detail level of the characteristic information. The traditional methods, such as human-computer interaction or using experienced values, are often influenced by subjective factors. They can neither determine the threshold automatically nor be applied to all situations. Therefore, studying on the automatic selection threshold methods is an important subject for image segmentation and worth further research.
By now, there is no certain threshold algorithm suitable for all types of images. Certainly for specific images and specific requirements, we can find the optimum threshold methods with quite good effect. This paper studies and discusses several automatic selection threshold methods for simple and complex images separately. Since the latter is based on the former, this paper is focus on global threshold in simple images.
Global threshold method based on pixel gray scale can be used in a simple remote sensing image. While iterative method can be used in the uniform illumination images which have double-peak and deep-valley histogram. When there are higher real-time and stability requirements, the minimum error method is a better choice. Maximum entropy method can not only be applied to the images with low gray contrast and single-peak histogram, but also be applied to small targets extraction; however, it is sensitivity to noise. For the images that with the suitable size of target, the maximum between-class variance method can be used to find the optimal threshold for image segmentation. Minimum cross-entropy threshold method focuses on minimizing the discrepancies of information between the original image and segmented image, it has high applicability in images with single-peak histogram as well as double-peak histogram; but, it is sensitivity to the size of the target.
For the remote sensing images with much noise and non-uniform background characteristics, the threshold method based on attributes of pixel neighborhood is more appropriate. This article develops one-dimensional Otsu algorithm and one-dimensional maximum entropy method to two-dimensional space; and also proposes an algorithm based on edge weighting. All of them can effectively overcome the noise interference, and the segmentation results are better than the one-dimensional threshold algorithm. However, the computation time of the two-dimensional algorithm is much longer than the one-dimensional algorithm due to the multiplied computation.
As for complex remote sensing images which have relatively rich gray levels, fuzzy boundaries, complex structure and different contrast, adaptive threshold method based on local properties can be used to segment the image. Mean method and Median method take the mean and median value of each pixel in an operator window as the threshold, which can greatly simplify the algorithm of traditional interpolation method. It takes the different characteristics of each part of the image into account, and can be success in segmentation.
对已有的研究成果分析表明,目前尚没有一种适合于所有图像的通用的阈值自动选取算法。但是,对于具体的图像、具体的需求,的确可以找到效果相当好的自动化阈值选取方法。本文分别对简单图像和复杂图像中阂值的自动选取方法进行了介绍并进行实验。由于后者基于前者,所以本文重点讨论简单图像中的阈值选取方法。
简单遥感图像采用阈值分割时,可使用基于像元灰度的全局阈值法。在保持图像的均匀照度下,对于直方图双峰明显,谷底较深的图像,可采用迭代法；对目标大小适合的图像,可采用最大类间方差法寻找最佳阈值进行图像分割；实时性和稳定性要求高时可选择最小误差法；当图像中目标和背景灰度对比度较低,直方图为单峰,或者目标与背景比例不均衡,目标地物比较小时,可采用最大熵法,但其对噪声点比较敏感；当注重原始图像和分割后图像之间的信息量差异最小时,可采用最小交叉熵阈值法,它在双峰图像和单峰图像中的适用性都很高,但它对目标的大小较敏感。
简单遥感图像中含有噪声,背景灰度不均匀时,可使用基于像元邻域属性的阈值法。本文将一维Otsu算法和一维最大熵算法拓展到二维空间,提出了二维阈值算法；同时还提出一种过渡区加权的算法。这三种方法都能有效地克服噪声的干扰,分割效果总体上都优于一维阈值算法。但从运算时间来看,由于运算量成倍增加,二维算法的计算时间也高于一维算法。
复杂遥感图像中目标灰度层次比较丰富、边界模糊,物体和背景的对比度在图像中各处不一样,可使用局部自适应阈值法。Mean法和Median法对每个像素确定一个以它为中心的窗口,然后求取窗口内的灰度均值和中值作为此像素的阈值,最后移动窗口得到每个像素的阈值。这种方法大大简化了传统阈值差值的算法,并且能兼顾考虑图像各处的具体情况,保证分割效果。
In the application of remote sensing images, people are often interested in specific information of the image. When extracting the specific target information, it is necessary to separate the target from the whole original image and try to avoid the disturbances from the background. How to rationally and effectively obtain the threshold which is used to differentiate the object from the background is the key process. However, thresholds based on different segmentation algorithms would affect the precision of the result and the detail level of the characteristic information. The traditional methods, such as human-computer interaction or using experienced values, are often influenced by subjective factors. They can neither determine the threshold automatically nor be applied to all situations. Therefore, studying on the automatic selection threshold methods is an important subject for image segmentation and worth further research.
By now, there is no certain threshold algorithm suitable for all types of images. Certainly for specific images and specific requirements, we can find the optimum threshold methods with quite good effect. This paper studies and discusses several automatic selection threshold methods for simple and complex images separately. Since the latter is based on the former, this paper is focus on global threshold in simple images.
Global threshold method based on pixel gray scale can be used in a simple remote sensing image. While iterative method can be used in the uniform illumination images which have double-peak and deep-valley histogram. When there are higher real-time and stability requirements, the minimum error method is a better choice. Maximum entropy method can not only be applied to the images with low gray contrast and single-peak histogram, but also be applied to small targets extraction; however, it is sensitivity to noise. For the images that with the suitable size of target, the maximum between-class variance method can be used to find the optimal threshold for image segmentation. Minimum cross-entropy threshold method focuses on minimizing the discrepancies of information between the original image and segmented image, it has high applicability in images with single-peak histogram as well as double-peak histogram; but, it is sensitivity to the size of the target.
For the remote sensing images with much noise and non-uniform background characteristics, the threshold method based on attributes of pixel neighborhood is more appropriate. This article develops one-dimensional Otsu algorithm and one-dimensional maximum entropy method to two-dimensional space; and also proposes an algorithm based on edge weighting. All of them can effectively overcome the noise interference, and the segmentation results are better than the one-dimensional threshold algorithm. However, the computation time of the two-dimensional algorithm is much longer than the one-dimensional algorithm due to the multiplied computation.
As for complex remote sensing images which have relatively rich gray levels, fuzzy boundaries, complex structure and different contrast, adaptive threshold method based on local properties can be used to segment the image. Mean method and Median method take the mean and median value of each pixel in an operator window as the threshold, which can greatly simplify the algorithm of traditional interpolation method. It takes the different characteristics of each part of the image into account, and can be success in segmentation.
引文
[1]Abutaleb A S.Automatic thresholding of gray-level pictures using two-dimensional entropies[J].Pattern Recognition,1989,47(1):22-32.
[2]Ahuja N, Rosenfeld A. A note on the use of second-order gray-level statisticsfor threshold selection. IEEE Irans. on System, Man,and Cybernetics,1978,8:895-899.
[3]Bahadir Karasulu, Serdar Korukoglu.A simulated annealing-based optimal threshold determining method in edge-based segmentation of grayscale images [J]. Applied Soft Computing.2011,11:2246-2259.
[4]Bartz M R. Optimizing a video preprocessor for OCR. In:Proc IJCAI,1969:79-90.
[5]Bernsen J. Dynamic thresholding of gray-level images. In Proc 8ICPR,1986:1251-1255.
[6]Brink A D.Thresholding of digital images using two-dimensional entropies[J]. Pattern Recognition,1992,25(8):803-808.
[7]Cheng H D,Chen Y H,Sun Y.A novel fuzzy entropy approach to image enhancement and thresholding[J].Signal Processing,1999,75(3)277-301.
[8]Chow C K, Kaneko T. Automatic boundary detection of left ventricle from cineangiograms. Comput Biomed Res,1972; 5:388-410.
[9]De Albuquerque M P,Esquef I A,Gesualdi Mello A R.Image thresholding using Tsallis entropy[J].Pattern Recognition Letters,2004,25(9):1059-1065.
[10]Doyle W. Operations useful for similarity-invariant pattern recognition [J]. Journal of the ACM,1962:9(2):259-267.
[11]Esin Guldogan and Moncef Gabbouj. Mapping by adaptive threshold method for dimension reduction of content-based indexing and retrieval features.
[12]Jichuan Shi. Adaptive local threshold with shape information and its application to oil sand image segmentation [D].Cananda:University of Alberta,2010.
[13]John canny, A Computational Approach to Edge Detection. IEEE transactions on pattern analysis and machine intelligence, vol. pami-8, no.6, november 1986.
[14]Kapur J N,Sahoo PK,Wong A K C. A new method for gray level picture thresholding using the entropy of the histogram[J].Computer Vision, Graphics and Image Process,1985, 29(3):273-285.
[15]Katz Y H. Pattern recognition of meteorological satellite cloud photography. In:Proc 3rd symp on Remote Sensing of environment,1965:172-214.
[16]Kittler J, Illingworth J,Foglein J.Threhsold selection based on a simple image statistic [J]. Computer Vision,Graphics and Image Processing,1985,30:125-147.
[17]Kittler J, Illingworth J. Minimum error thresholding. Pattern Recognition,1986; 19(1):41-47.
[18]Kittler J, Illingworth J. On threshold selection using clustering criteria [J]. IEEE Trans.Systems, Man and Cybernetics,1985,15(5):652-655.
[19]Kittler J,Illingworth J,Foglein J,Paler K. An automatic thresholding algorithm and its performance[C].In.Proc.seventh Int.conference,Pattern recognition. Vol.Montreal P.Q.Canada 1984:287-289.
[20]Lee S U, Chung S Y, Park R H. A comparative study of global thresholding techniques for segmentation. Computer Vision, Graphics and Image Processing,1990; 52:171-190.
[21]Magid A, Rotman S R, Weiss A M. Comment on "Picture thresholding using an iterative selection method". IEEE Trans,1990; SMC-20(5):1238-1239.
[22]Magid A, Rotman S R, Weiss A M. Comment on "Picture thresholding using an iterative selection method". IEEE Trans,1990; SMC-20(5):1238-1239.
[23]Mehmet Sezgin, Ramazan Tasaltin. A new dichotomization technique to multilevel thresholding devoted to inspection applications [J]. Pattern Recognition Letters.2000, 21:151-161.
[24]Mehmet Sezgin,Bulent Sankur. Survey over image thresholding techniquesand quantitative performance evaluation[J]. Journal of Electronic Imaging.2004,13(1):146-165.
[25]Nilanjan Ray, Baidya Nath Saha.Edge Sensitive Variational Image Thresholding.
[26]Nobuyuki otsu. A Threshold Selection Method from Gray-Level Histograms[J].IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS,1979,9(1):62-66.
[27]Olivo J C. Automatic threshold selection using the wavelet transform. Computer Vision, Graphics, and Image Processing,1994,56:205-218
[28]Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Trans.Systems Man and Cybernetics,1979,9(1):62-66.
[29]Pal N R,Pal S K.Entropic thresholding[J].Signal Process,1989,16:97-108.
[30]Pal S K,King R A,Hashim A A. Automatic gray level thresholding through index of fuzziness and entropy[J].Pattern Recognition Letters,1983,1:141-146.
[31]Panda D P, Rosenfeld A. Image segmentation by pixel classification in gray level, edge value space. IEEE Trans,1978; C-27(9):875-879.
[32]Patrick Dickinson, Andrew Hunter, Kofi Appiah.A spatially distributed model for foreground segmentation[J]. Image and Vision Computing.2009,27:1326-1335.
[33]Paul L. Rosin. Thresholding for Change Detection [J]. Computer Vision and Image Understanding.2002,86:79-95.
[34]Paul L.Rosin, Efstathios Ioannidis. Evaluation of global image thresholding for change detection[J]. Pattern Recognition Letters.2003,24:2345-2356.
[35]Peng-Yeng Yin.A fast scheme for optimal thresholding using genetic algorithms [J]. Signal Processing.1999,72:85-95.
[36]Prewitt J M S, Mendelsohn M L. The analysis of cell images. Ann N Y Acad Sci,1966; 128: 1035-1053.
[37]Pun T. A new method for grey-level picture thresholding using the entropy of the histogram [J].Signal Process,1980,2(3):223-237.
[38]Pun T. Entropic thresholding, a new method [J]. Computer Graphics and Image Process, 1981,16(3):210-239.
[39]R.Guo, S.M. Pandit. Automatic threshold selection based on histogram modes and a discriminant criterion [J]. Machine Vision and Applications.1998,10:331-338.
[40]Rosenfeld A, Torre P. Histogram concavity analysis as an aid in threshold selection[J].IEEE Trans.Systems Man and Cybernetics,1983,13(3):231-235.
[41]Rafael C.Gonzalez等著阮秋琦等译.数字图像处理(MATLAB版).电子工业出版社.2006.
[42]Sahoo P K et al. A survey of thresholding techniques. Computer Vision, Graphics and Image Processing,1988; 41:233-260.
[43]Sahoo P K,Arora G.A thresholding method based on two-dimensional Renyi'sentropy [J].Pattern Recognition.2004,37(6):1149-1161.
[44]Sahoo P K,Wilkins C,Yeager J.Threshold selection using Renyi's entropy[J]. Pattern Recognition,1997,30(1):71-84.
[45]Shao-shan Chiang. Automatic target detection and classification for hyperspectral imagery[D]. America:University of Maryland,2001.
[46]Shi Bao-shan, Zhang Fa-quan. A Method for Threshold Selection in Edge Width Detection of Objects in the Image [J].International Conference on Signal Processing Systems.2009:402-405.
[47]Sreenath Rao Vantaram. Fast unsupervised multiresolution colorimage segmentation using adaptive gradeintthresholding and progressive regiongrowing[D]. America:ROCHESTER INSTITUTE OF TECHNOLOGY,2009.
[48]Svetha venkatesh. Dynamic threshold determination by local and global edge evaluation[J]. Graphical models and image processing.1995,57(2):146-160.
[49]Trier D,Taxt T.Evaluation of binarization methods for document images. IEEE-PAMI,1995, 17(3):312-315.
[50]Trussel H J. Comments on "Picture thresholding using an iterative selection method", IEEE Trans,1979; SMC-9(9):311.
[51]Trussel H J. Comments on "Picture thresholding using an iterative selection method", IEEE Trans,1979; SMC-9(9):311.
[52]Tsai W H. Moment-preserving thresholding:A new approach[J].Computer Vision,Graphics and Image Processing,1985,29(3):377-393.
[53]Weszka J S, Rosenfeld A. Histogram modification for threshold selection. IEEEans. on System, Man, and Cybernetics,1979,9(1):38-52
[54]Y.J. zhang. A survey on evaluation methods for image segementation[J]. Pattern Recognition.1996,29(8):1335-1346.
[55]Yanowitz S D, Bruckstein A M. A new method for image segmentation. In:Proc 9ICPR,1988: 270-275.
[56]Yen J G,Chang F J,Chang S.A new criterion for automatic multilevel thresholding[J].IEEE Trans.Image Processing,1995,4(3):233-260.
[57]Yen J G,Chang F J,Chang S.A new criterion for automatic multilevel thresholding[J].IEEE Trans.Image Processing,1995,4(3):233-260.
[58]Yinxiao Liu. A new method of threshold and gradient optimization using class uncertainty theory and its quantitative analysis [D]. America:University of Iowa,2009.
[59]YIXIN CHEN.New techniques for image de-nosing,thresholding,object detection and their application to vision based collision avoidance system[D]. America:University of Oakland,2008.
[60]ZHANG Y J, GERBRANDS J J. Objective and quantitative segmentation evaluation and comparison [J]. Signal Processing,1994,39(1/2):43-54
[61]曹力,史忠科.基于最大熵原理的多阈值自动选取新方法[J].中国图像图形学报.2002,7(5)：461-465.
[62]陈果,左洪福.图像自适应模糊阈值分割法[J].自动化学报.2003,29(5)：791-796.
[63]陈静,张世杰.基于动态自适应阈值法的QRS波群检测方法[J].中国新通信.2009,2：67-69.
[64]陈科,张保明,谢明霞.模糊Bayes理论在遥感影像变化检测中的应用[J].计算机工程与应用.2010,46(19)：185-188.
[65]陈敏.一种自动识别最优阈值的图像分割方法[J].计算机应用与软件.2006,23(4)：85-86.
[66]陈琪,熊博莅,陆军.二维类内最小交叉熵的图像分割快速方法[J].计算机工程与应用.2011,47(9)：149-151.
[67]初青瑜MAT LAB在图像处理中的应用[J].信息技术与信息化.2010,4(55).
[68]褚巧龙.基于Otsu的图像阂值分割算法的研究[D].燕山大学,2011.
[69]崔天意,刘文萍,张宁.遥感图像林区自动阈值分割算法及性能比较[J].计算机应用.2010,30(12)：3269-3273.
[70]东秀阁.基于信息熵的图像分割方法研究及其在DSP中的快速实现[D].天津大学,2003
[71]东秀阁.基于信息熵的图像分割方法研究及其在DSP中的快速实现[D].天津大学,2003.
[72]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.
[73]杜奇,向健勇,袁胜春.基于边缘强度的红外图像闽值分割方法研究[J].红外与激光工程.2004,33(3)：288-291.
[74]范九伦,雷博.灰度图像最小误差阈值分割法的二维推广[J].自动化学报.2009,35(4)：386-393.
[75]付忠良.图像阈值选取方法-Otsu方法的推广[J].计算机应用.2000,20(5)：37-39.
[76]付忠良.图像阈值选取方法的构造[J].中国图象图形学报.2000,5(6)：466-469.
[77]付忠良.一些新的图像阈值选取方法[J].计算机应用.2000,20(10)：13-15.
[78]高月红.灰度图像分割算法的研究[J].科技信息.2009,27：409-410.
[79]郭臻,陈远知.图像阂值分割算法研究[J].中国传媒大学学报自然科学版.2008,15(2)：76-82.
[80]韩青松.基于Otsu算法的遥感图像阈值分割[D].新疆大学,2011.
[81]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.
[82]何春华,胡迎春.基于改进遗传算法的自动阈值图像分割方法[J].计算机仿真.2011,28(2)：312-315.
[83]胡珂立,赵鲁阳.一种改进的自适应阈值前景提取方法[J].计算机应用研究.2011,28(12)：4726-4729.
[84]蒋艳军,谭佐军,余贞贞,陈建军.红外图像阈值分割算法的研究[J].红外.2008,29(12)：33-35.
[85]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算法[J].通信学报.2001,22(4)：7]-76.
[86]雷博,范九伦.灰度图像二维交叉熵阈值分割法[J].光子学报.2009,38(6)：1572-1576.
[87]李刚,杨锦园.基于遗传算法的自动阈值选取方法研究[J].计算机与数字工程.2009,1：34-37.
[88]李哲,黄廉卿.基于自动选取最佳阈值的X光图像快速分割方法[J].计算机应用研究.2007,24(3)：286-288.
[89]李峥嵘.图像分割多阈值法在CT图像重建中的应用[D].合肥工业大学,2007.
[90]李佐勇.基于统计和谱图的图像阈值分割方法研究[D].南京理工大学,2010.
[91]林瑶,田捷.医学图像分割方法综述[J].1-14.
[92]刘杰,安博文.基于动态阈值分割的目标提取技术[J].红外技术.2008,30(12)：706-709.
[93]刘娜.基于微粒群算法的图像阈值分割方法及其应用[D].中南民族大学,2008.
[94]刘爽.图象分割中阈值选取方法的研究及其算法实现[J].电脑知识与技术.2005,68-69.
[95]刘文萍吴立德.图像分割中阈值选取方法比较研究[J].模式识别与人工智能.1997,10(3)：271-277.
[96]龙建武.基于Otsu的图像阈值分割算法的研究[D].吉林大学,2011.
[97]卢桂馥,范影乐,庞全.基于边缘检测的二值化方法研究[J].计量技术.2003,12：3-5.
[98]罗三定,谭晓东.图像分割中最佳阈值集的选择与评测[J].计算机与信息技术.17-19.
[99]罗文村,郭伟斌.图像阈值分割方法的比较与分析[J].应用技术.2000,11：22-25.
[100]吕俊哲.图像二值化算法研究及其实现[J].科学情报发展与经济.2004,14(12)：266-267.
[101]吕燕.基于阈值算法图像分割的研究[D].重庆大学,2011.
[102]欧阳鑫玉,赵楠楠,宋蕾等.鞍山钢铁学院学报[J].光电工程.2002,25(5)：363-368.
[103]潘春雨,卢志刚,秦嘉.基于区域阈值的图像分割方法研究[J]火力与指挥控制.2011,36(1)：118-122.
[104]潘喆,吴一全.二维指数熵图像闽值选取方法及其快速算法[J].计算机应用.2007,27(4)：982-985.
[105]彭丽.基于边缘信息的闽值图像分割[D].中南大学,2009.
[106]秦囊培.MATLAB图像处理与界面编程宝典(M).电子工业出版社.2009.
[107]瞿继双,王超,王正志.一种基于多阈值的形态学提取遥感图象海岸线特征方法[J].中国图象图形学报.2003,8(7)：805-809.
[108]瞿中.基于改进的最大类间方差算法的图像分割研究[J].计算机科学.2009,36(5)：276-279.
[109]唐清.阈值分割及红外图像行人检测研究[D].华南理工大学,2010.
[110]唐闻.结合形态学的基于闽值分割方法在MR脑实质图像提取中的应用研究[D].中南大学,2009.
[111]涂望明,魏友国,施少敏.MATLAB在数字图像处理中的应用[J].微计算机信息.2007,23(2-3)：299-301.
[112]王鹤智,刘兆刚.阈值分割和数学形态学在遥感图像边缘提取中的应用[J].森林工程.2009,25(2)：9-12.
[113]王亮亮,王黎.两种改进的局部阈值分割算法[J].现代电子技术.2009,14：78-80.
[114]王敏,骆惠,黄心汉.一种新的自动多阈值图像分割方法[J].信号处理.2000,16(1)：90-94.
[115]王培.遗传算法在图像阈值分割中的应用研究[D].太原理工大学,2005.
[116]王强.图像分割中阈值的选取研究及算法实现[J].计算机与现代化.2006,10：54-56.
[117]王任挥.基于最大信息熵原理的显微细胞图像多阈值分割[D].内蒙古师范大学,2008.
[118]王润生.图像理解(M).国防科技大学出版社.1995.
[119]王苑楠.图像边缘检测方法的比较和研究[J].计算机与数字工程.2009,1：121-124.
[120]韦玉春,汤国安,杨听等.遥感数字图像处理教程(M).科学出版社.2008.
[121]魏伟,李战明,张国权.基于二维最小Tsallis交叉熵和遗传算法的快速图像分割[J].昆明理工大学学报(理工版).2010,35(5)：61-65.
[122]吴冰,秦志远.自动确定图像二值化最佳阈值的新方法[J].测绘学院学报.2001,18(4)：283-286.
[123]吴一全,张晓杰,吴诗嬉.2维对称交叉熵图像阈值分割[J].中国图象图形学报.2011,16(8)：1393-1401.
[124]吴一全,朱兆达.图像处理中闽值选取方法30年(1962-1992)的进展[J].数据采集与处理.1993,8(3)：193-201,268-282.
[125]熊福松.基于阈值选取的图像分割方法研究-Parzen窗技术在阈值分割方法中的应用[D].江南大学,2007.
[126]徐亚明.基于边缘检测的红外图像二值化算法[J].34-35.
[127]杨金龙,张光南.基于二维直方图的图像分割算法研究[J].激光与红 外.2008,38(4)：400-403.
[128]杨修国.图像阈值分割方法的研究与分析[D].华东师范大学,2009.
[129]袁晓辉,许东.基于形态学滤波和分水线算法的目标图像分割[J].数据采集与处理.2003,18(4)：455-459.
[130]张春玲.图像的阈值分割及其应用[J].泰山医学院学报.2006,27(3)：200-201.
[131]张冬生.基于阈值的图像分割算法研究[D].东北石油大学,2011.
[132]张庆英,岳卫宏,肖维红,江霞.基于边界特征的图像二值化方法应用研究[J].武汉理工大学学报.2005,27(2)：55-58.
[133]张伟,蒋宏,任章.自适应多阈值图像分割算法[J].模式识别与仿真.2007,26(8)：71-74.
[134]张新明,党留群.一种改进的二维最小交叉熵图像分割方法[J].光电工程.2010,37(11)：103-109.
[135]张新明,党留群.一种改进的二维最小交叉熵图像分割方法[J].光电工程.2010,37(11)：103-109.
[136]张新明,孙印杰.最大熵和最小交叉熵综合的交互式图像分割[J].计算机工程与应.2010,46(30)：191-194.
[137]张阳洁.基于阈值的图像分割技术在简牍中的应用[D].成都理工大学,2010.
[138]郑南,徐忠林.改进的自适应阈值区域图像分割方法在飞机目标识别中的应用[J].电脑编程技巧与维护.2010,134-135.
[139]周德龙,中石磊.基于灰度-梯度共生矩阵模型的最大熵阈值处理算法[J].小型微型计算机系统.2002,23(2)：136-138.
[140]朱雪龙.应用信息论基础[M].北京：清华大学出版社,2001.
[2]Ahuja N, Rosenfeld A. A note on the use of second-order gray-level statisticsfor threshold selection. IEEE Irans. on System, Man,and Cybernetics,1978,8:895-899.
[3]Bahadir Karasulu, Serdar Korukoglu.A simulated annealing-based optimal threshold determining method in edge-based segmentation of grayscale images [J]. Applied Soft Computing.2011,11:2246-2259.
[4]Bartz M R. Optimizing a video preprocessor for OCR. In:Proc IJCAI,1969:79-90.
[5]Bernsen J. Dynamic thresholding of gray-level images. In Proc 8ICPR,1986:1251-1255.
[6]Brink A D.Thresholding of digital images using two-dimensional entropies[J]. Pattern Recognition,1992,25(8):803-808.
[7]Cheng H D,Chen Y H,Sun Y.A novel fuzzy entropy approach to image enhancement and thresholding[J].Signal Processing,1999,75(3)277-301.
[8]Chow C K, Kaneko T. Automatic boundary detection of left ventricle from cineangiograms. Comput Biomed Res,1972; 5:388-410.
[9]De Albuquerque M P,Esquef I A,Gesualdi Mello A R.Image thresholding using Tsallis entropy[J].Pattern Recognition Letters,2004,25(9):1059-1065.
[10]Doyle W. Operations useful for similarity-invariant pattern recognition [J]. Journal of the ACM,1962:9(2):259-267.
[11]Esin Guldogan and Moncef Gabbouj. Mapping by adaptive threshold method for dimension reduction of content-based indexing and retrieval features.
[12]Jichuan Shi. Adaptive local threshold with shape information and its application to oil sand image segmentation [D].Cananda:University of Alberta,2010.
[13]John canny, A Computational Approach to Edge Detection. IEEE transactions on pattern analysis and machine intelligence, vol. pami-8, no.6, november 1986.
[14]Kapur J N,Sahoo PK,Wong A K C. A new method for gray level picture thresholding using the entropy of the histogram[J].Computer Vision, Graphics and Image Process,1985, 29(3):273-285.
[15]Katz Y H. Pattern recognition of meteorological satellite cloud photography. In:Proc 3rd symp on Remote Sensing of environment,1965:172-214.
[16]Kittler J, Illingworth J,Foglein J.Threhsold selection based on a simple image statistic [J]. Computer Vision,Graphics and Image Processing,1985,30:125-147.
[17]Kittler J, Illingworth J. Minimum error thresholding. Pattern Recognition,1986; 19(1):41-47.
[18]Kittler J, Illingworth J. On threshold selection using clustering criteria [J]. IEEE Trans.Systems, Man and Cybernetics,1985,15(5):652-655.
[19]Kittler J,Illingworth J,Foglein J,Paler K. An automatic thresholding algorithm and its performance[C].In.Proc.seventh Int.conference,Pattern recognition. Vol.Montreal P.Q.Canada 1984:287-289.
[20]Lee S U, Chung S Y, Park R H. A comparative study of global thresholding techniques for segmentation. Computer Vision, Graphics and Image Processing,1990; 52:171-190.
[21]Magid A, Rotman S R, Weiss A M. Comment on "Picture thresholding using an iterative selection method". IEEE Trans,1990; SMC-20(5):1238-1239.
[22]Magid A, Rotman S R, Weiss A M. Comment on "Picture thresholding using an iterative selection method". IEEE Trans,1990; SMC-20(5):1238-1239.
[23]Mehmet Sezgin, Ramazan Tasaltin. A new dichotomization technique to multilevel thresholding devoted to inspection applications [J]. Pattern Recognition Letters.2000, 21:151-161.
[24]Mehmet Sezgin,Bulent Sankur. Survey over image thresholding techniquesand quantitative performance evaluation[J]. Journal of Electronic Imaging.2004,13(1):146-165.
[25]Nilanjan Ray, Baidya Nath Saha.Edge Sensitive Variational Image Thresholding.
[26]Nobuyuki otsu. A Threshold Selection Method from Gray-Level Histograms[J].IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS,1979,9(1):62-66.
[27]Olivo J C. Automatic threshold selection using the wavelet transform. Computer Vision, Graphics, and Image Processing,1994,56:205-218
[28]Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Trans.Systems Man and Cybernetics,1979,9(1):62-66.
[29]Pal N R,Pal S K.Entropic thresholding[J].Signal Process,1989,16:97-108.
[30]Pal S K,King R A,Hashim A A. Automatic gray level thresholding through index of fuzziness and entropy[J].Pattern Recognition Letters,1983,1:141-146.
[31]Panda D P, Rosenfeld A. Image segmentation by pixel classification in gray level, edge value space. IEEE Trans,1978; C-27(9):875-879.
[32]Patrick Dickinson, Andrew Hunter, Kofi Appiah.A spatially distributed model for foreground segmentation[J]. Image and Vision Computing.2009,27:1326-1335.
[33]Paul L. Rosin. Thresholding for Change Detection [J]. Computer Vision and Image Understanding.2002,86:79-95.
[34]Paul L.Rosin, Efstathios Ioannidis. Evaluation of global image thresholding for change detection[J]. Pattern Recognition Letters.2003,24:2345-2356.
[35]Peng-Yeng Yin.A fast scheme for optimal thresholding using genetic algorithms [J]. Signal Processing.1999,72:85-95.
[36]Prewitt J M S, Mendelsohn M L. The analysis of cell images. Ann N Y Acad Sci,1966; 128: 1035-1053.
[37]Pun T. A new method for grey-level picture thresholding using the entropy of the histogram [J].Signal Process,1980,2(3):223-237.
[38]Pun T. Entropic thresholding, a new method [J]. Computer Graphics and Image Process, 1981,16(3):210-239.
[39]R.Guo, S.M. Pandit. Automatic threshold selection based on histogram modes and a discriminant criterion [J]. Machine Vision and Applications.1998,10:331-338.
[40]Rosenfeld A, Torre P. Histogram concavity analysis as an aid in threshold selection[J].IEEE Trans.Systems Man and Cybernetics,1983,13(3):231-235.
[41]Rafael C.Gonzalez等著阮秋琦等译.数字图像处理(MATLAB版).电子工业出版社.2006.
[42]Sahoo P K et al. A survey of thresholding techniques. Computer Vision, Graphics and Image Processing,1988; 41:233-260.
[43]Sahoo P K,Arora G.A thresholding method based on two-dimensional Renyi'sentropy [J].Pattern Recognition.2004,37(6):1149-1161.
[44]Sahoo P K,Wilkins C,Yeager J.Threshold selection using Renyi's entropy[J]. Pattern Recognition,1997,30(1):71-84.
[45]Shao-shan Chiang. Automatic target detection and classification for hyperspectral imagery[D]. America:University of Maryland,2001.
[46]Shi Bao-shan, Zhang Fa-quan. A Method for Threshold Selection in Edge Width Detection of Objects in the Image [J].International Conference on Signal Processing Systems.2009:402-405.
[47]Sreenath Rao Vantaram. Fast unsupervised multiresolution colorimage segmentation using adaptive gradeintthresholding and progressive regiongrowing[D]. America:ROCHESTER INSTITUTE OF TECHNOLOGY,2009.
[48]Svetha venkatesh. Dynamic threshold determination by local and global edge evaluation[J]. Graphical models and image processing.1995,57(2):146-160.
[49]Trier D,Taxt T.Evaluation of binarization methods for document images. IEEE-PAMI,1995, 17(3):312-315.
[50]Trussel H J. Comments on "Picture thresholding using an iterative selection method", IEEE Trans,1979; SMC-9(9):311.
[51]Trussel H J. Comments on "Picture thresholding using an iterative selection method", IEEE Trans,1979; SMC-9(9):311.
[52]Tsai W H. Moment-preserving thresholding:A new approach[J].Computer Vision,Graphics and Image Processing,1985,29(3):377-393.
[53]Weszka J S, Rosenfeld A. Histogram modification for threshold selection. IEEEans. on System, Man, and Cybernetics,1979,9(1):38-52
[54]Y.J. zhang. A survey on evaluation methods for image segementation[J]. Pattern Recognition.1996,29(8):1335-1346.
[55]Yanowitz S D, Bruckstein A M. A new method for image segmentation. In:Proc 9ICPR,1988: 270-275.
[56]Yen J G,Chang F J,Chang S.A new criterion for automatic multilevel thresholding[J].IEEE Trans.Image Processing,1995,4(3):233-260.
[57]Yen J G,Chang F J,Chang S.A new criterion for automatic multilevel thresholding[J].IEEE Trans.Image Processing,1995,4(3):233-260.
[58]Yinxiao Liu. A new method of threshold and gradient optimization using class uncertainty theory and its quantitative analysis [D]. America:University of Iowa,2009.
[59]YIXIN CHEN.New techniques for image de-nosing,thresholding,object detection and their application to vision based collision avoidance system[D]. America:University of Oakland,2008.
[60]ZHANG Y J, GERBRANDS J J. Objective and quantitative segmentation evaluation and comparison [J]. Signal Processing,1994,39(1/2):43-54
[61]曹力,史忠科.基于最大熵原理的多阈值自动选取新方法[J].中国图像图形学报.2002,7(5)：461-465.
[62]陈果,左洪福.图像自适应模糊阈值分割法[J].自动化学报.2003,29(5)：791-796.
[63]陈静,张世杰.基于动态自适应阈值法的QRS波群检测方法[J].中国新通信.2009,2：67-69.
[64]陈科,张保明,谢明霞.模糊Bayes理论在遥感影像变化检测中的应用[J].计算机工程与应用.2010,46(19)：185-188.
[65]陈敏.一种自动识别最优阈值的图像分割方法[J].计算机应用与软件.2006,23(4)：85-86.
[66]陈琪,熊博莅,陆军.二维类内最小交叉熵的图像分割快速方法[J].计算机工程与应用.2011,47(9)：149-151.
[67]初青瑜MAT LAB在图像处理中的应用[J].信息技术与信息化.2010,4(55).
[68]褚巧龙.基于Otsu的图像阂值分割算法的研究[D].燕山大学,2011.
[69]崔天意,刘文萍,张宁.遥感图像林区自动阈值分割算法及性能比较[J].计算机应用.2010,30(12)：3269-3273.
[70]东秀阁.基于信息熵的图像分割方法研究及其在DSP中的快速实现[D].天津大学,2003
[71]东秀阁.基于信息熵的图像分割方法研究及其在DSP中的快速实现[D].天津大学,2003.
[72]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.
[73]杜奇,向健勇,袁胜春.基于边缘强度的红外图像闽值分割方法研究[J].红外与激光工程.2004,33(3)：288-291.
[74]范九伦,雷博.灰度图像最小误差阈值分割法的二维推广[J].自动化学报.2009,35(4)：386-393.
[75]付忠良.图像阈值选取方法-Otsu方法的推广[J].计算机应用.2000,20(5)：37-39.
[76]付忠良.图像阈值选取方法的构造[J].中国图象图形学报.2000,5(6)：466-469.
[77]付忠良.一些新的图像阈值选取方法[J].计算机应用.2000,20(10)：13-15.
[78]高月红.灰度图像分割算法的研究[J].科技信息.2009,27：409-410.
[79]郭臻,陈远知.图像阂值分割算法研究[J].中国传媒大学学报自然科学版.2008,15(2)：76-82.
[80]韩青松.基于Otsu算法的遥感图像阈值分割[D].新疆大学,2011.
[81]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.
[82]何春华,胡迎春.基于改进遗传算法的自动阈值图像分割方法[J].计算机仿真.2011,28(2)：312-315.
[83]胡珂立,赵鲁阳.一种改进的自适应阈值前景提取方法[J].计算机应用研究.2011,28(12)：4726-4729.
[84]蒋艳军,谭佐军,余贞贞,陈建军.红外图像阈值分割算法的研究[J].红外.2008,29(12)：33-35.
[85]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算法[J].通信学报.2001,22(4)：7]-76.
[86]雷博,范九伦.灰度图像二维交叉熵阈值分割法[J].光子学报.2009,38(6)：1572-1576.
[87]李刚,杨锦园.基于遗传算法的自动阈值选取方法研究[J].计算机与数字工程.2009,1：34-37.
[88]李哲,黄廉卿.基于自动选取最佳阈值的X光图像快速分割方法[J].计算机应用研究.2007,24(3)：286-288.
[89]李峥嵘.图像分割多阈值法在CT图像重建中的应用[D].合肥工业大学,2007.
[90]李佐勇.基于统计和谱图的图像阈值分割方法研究[D].南京理工大学,2010.
[91]林瑶,田捷.医学图像分割方法综述[J].1-14.
[92]刘杰,安博文.基于动态阈值分割的目标提取技术[J].红外技术.2008,30(12)：706-709.
[93]刘娜.基于微粒群算法的图像阈值分割方法及其应用[D].中南民族大学,2008.
[94]刘爽.图象分割中阈值选取方法的研究及其算法实现[J].电脑知识与技术.2005,68-69.
[95]刘文萍吴立德.图像分割中阈值选取方法比较研究[J].模式识别与人工智能.1997,10(3)：271-277.
[96]龙建武.基于Otsu的图像阈值分割算法的研究[D].吉林大学,2011.
[97]卢桂馥,范影乐,庞全.基于边缘检测的二值化方法研究[J].计量技术.2003,12：3-5.
[98]罗三定,谭晓东.图像分割中最佳阈值集的选择与评测[J].计算机与信息技术.17-19.
[99]罗文村,郭伟斌.图像阈值分割方法的比较与分析[J].应用技术.2000,11：22-25.
[100]吕俊哲.图像二值化算法研究及其实现[J].科学情报发展与经济.2004,14(12)：266-267.
[101]吕燕.基于阈值算法图像分割的研究[D].重庆大学,2011.
[102]欧阳鑫玉,赵楠楠,宋蕾等.鞍山钢铁学院学报[J].光电工程.2002,25(5)：363-368.
[103]潘春雨,卢志刚,秦嘉.基于区域阈值的图像分割方法研究[J]火力与指挥控制.2011,36(1)：118-122.
[104]潘喆,吴一全.二维指数熵图像闽值选取方法及其快速算法[J].计算机应用.2007,27(4)：982-985.
[105]彭丽.基于边缘信息的闽值图像分割[D].中南大学,2009.
[106]秦囊培.MATLAB图像处理与界面编程宝典(M).电子工业出版社.2009.
[107]瞿继双,王超,王正志.一种基于多阈值的形态学提取遥感图象海岸线特征方法[J].中国图象图形学报.2003,8(7)：805-809.
[108]瞿中.基于改进的最大类间方差算法的图像分割研究[J].计算机科学.2009,36(5)：276-279.
[109]唐清.阈值分割及红外图像行人检测研究[D].华南理工大学,2010.
[110]唐闻.结合形态学的基于闽值分割方法在MR脑实质图像提取中的应用研究[D].中南大学,2009.
[111]涂望明,魏友国,施少敏.MATLAB在数字图像处理中的应用[J].微计算机信息.2007,23(2-3)：299-301.
[112]王鹤智,刘兆刚.阈值分割和数学形态学在遥感图像边缘提取中的应用[J].森林工程.2009,25(2)：9-12.
[113]王亮亮,王黎.两种改进的局部阈值分割算法[J].现代电子技术.2009,14：78-80.
[114]王敏,骆惠,黄心汉.一种新的自动多阈值图像分割方法[J].信号处理.2000,16(1)：90-94.
[115]王培.遗传算法在图像阈值分割中的应用研究[D].太原理工大学,2005.
[116]王强.图像分割中阈值的选取研究及算法实现[J].计算机与现代化.2006,10：54-56.
[117]王任挥.基于最大信息熵原理的显微细胞图像多阈值分割[D].内蒙古师范大学,2008.
[118]王润生.图像理解(M).国防科技大学出版社.1995.
[119]王苑楠.图像边缘检测方法的比较和研究[J].计算机与数字工程.2009,1：121-124.
[120]韦玉春,汤国安,杨听等.遥感数字图像处理教程(M).科学出版社.2008.
[121]魏伟,李战明,张国权.基于二维最小Tsallis交叉熵和遗传算法的快速图像分割[J].昆明理工大学学报(理工版).2010,35(5)：61-65.
[122]吴冰,秦志远.自动确定图像二值化最佳阈值的新方法[J].测绘学院学报.2001,18(4)：283-286.
[123]吴一全,张晓杰,吴诗嬉.2维对称交叉熵图像阈值分割[J].中国图象图形学报.2011,16(8)：1393-1401.
[124]吴一全,朱兆达.图像处理中闽值选取方法30年(1962-1992)的进展[J].数据采集与处理.1993,8(3)：193-201,268-282.
[125]熊福松.基于阈值选取的图像分割方法研究-Parzen窗技术在阈值分割方法中的应用[D].江南大学,2007.
[126]徐亚明.基于边缘检测的红外图像二值化算法[J].34-35.
[127]杨金龙,张光南.基于二维直方图的图像分割算法研究[J].激光与红 外.2008,38(4)：400-403.
[128]杨修国.图像阈值分割方法的研究与分析[D].华东师范大学,2009.
[129]袁晓辉,许东.基于形态学滤波和分水线算法的目标图像分割[J].数据采集与处理.2003,18(4)：455-459.
[130]张春玲.图像的阈值分割及其应用[J].泰山医学院学报.2006,27(3)：200-201.
[131]张冬生.基于阈值的图像分割算法研究[D].东北石油大学,2011.
[132]张庆英,岳卫宏,肖维红,江霞.基于边界特征的图像二值化方法应用研究[J].武汉理工大学学报.2005,27(2)：55-58.
[133]张伟,蒋宏,任章.自适应多阈值图像分割算法[J].模式识别与仿真.2007,26(8)：71-74.
[134]张新明,党留群.一种改进的二维最小交叉熵图像分割方法[J].光电工程.2010,37(11)：103-109.
[135]张新明,党留群.一种改进的二维最小交叉熵图像分割方法[J].光电工程.2010,37(11)：103-109.
[136]张新明,孙印杰.最大熵和最小交叉熵综合的交互式图像分割[J].计算机工程与应.2010,46(30)：191-194.
[137]张阳洁.基于阈值的图像分割技术在简牍中的应用[D].成都理工大学,2010.
[138]郑南,徐忠林.改进的自适应阈值区域图像分割方法在飞机目标识别中的应用[J].电脑编程技巧与维护.2010,134-135.
[139]周德龙,中石磊.基于灰度-梯度共生矩阵模型的最大熵阈值处理算法[J].小型微型计算机系统.2002,23(2)：136-138.
[140]朱雪龙.应用信息论基础[M].北京：清华大学出版社,2001.