超声医学图像处理中若干问题的研究
|
摘要
中文摘要
超声心动图的心室容积测量是超声医学图像分割技术的典型应用；图像边
缘模糊给心室容积测量的实践带来了很大的困难。本研究从这一典型应用出发，
首先以小波变换理论为基础进行了超声医学图像噪声抑制及边缘检测方法的研
究，接着在此基础上开展了基于纹理的图像分割方法的研究。
本文在吸收前人成果和分析研究的基础上将小波变换、模糊集、粗糙集、
马尔可夫随机场、特征空间聚类等理论和方法应用于超声医学图像处理，以此
为基础提出了几种组合方法并对一些方法进行了改进。这些组合方法和改进的
方法在超声医学图像处理实验中取得了满意的效果。
本论文的主要创新表现在以下方面：
改进了小波收缩噪声抑制技术，将在小波系数域进行的收缩改进到小波矢
量模值域上进行；根据统计知识和李氏指数的理论推导出了各个阶次噪声抑制
阈值统一公式。
将粗糙集理论和旋转邻域技术应用于超声医学图像噪声抑制，通过定义噪
声集合的条件属性集定义了噪声粗糙集，并分别利用上逼近集合和下逼近集合
对图像进行了噪声抑制处理；在基于粗糙集的噪声抑制基础上提出了基于粗糙
集的孤立点抑制方法，基于粗糙集的边缘提取方法和基于粗糙集的区域边缘提
取方法，并利用这些方法对纹理分割后的图像进行了处理。
将小波变换多尺度边缘检测和模糊边缘检测方法有机的结合起来，提出了
小波模糊算子边缘检测方法；将小波变换边缘检测的多尺度检测结果作为模糊
集处理的对象，以离散形式给出了多尺度边缘对图像边缘集合的多变量模糊隶
属度函数，构成边缘集合的模糊隶属度矩阵（模糊特征平面）；采用分界点可调
的模糊增强算子对模糊隶属度矩阵进行增强以获得最终的边缘检测结果。小波
模糊算子边缘检测方法通过把小波变换的多尺度特性和模糊集善于处理不确定
性问题的优点结合起来，有效了解决了精确定位和有效检出的矛盾。
以马尔可夫随机过程和梯度小波变换为基础提出了梯度小波纹理模型；多
尺度的梯度小波纹理模型参数形成一个多尺度纹理特征空间，采用特征空间聚
类方法可以实现超声医学图像的纹理分割；我们在聚类过程中将较大尺度的聚
类结果作为较小尺度的聚类初始值提高了聚类过程的效率。梯度小波纹理模型
利用了马尔可夫随机场图像模型的优点和基于该模型的成熟方法，并且引入多
尺度、多分辨率特性。
本文通过客观评价方法对本文使用的图像处理方法进行了评价。评价结果
I
中文摘要
显示小波收缩噪声抑制技术和基于粗糙集的噪声抑制技术能有效地抑制图像中
的散斑噪声，小波模糊算子边缘检测方法有良好的边缘提取能力和抗噪声性能，
基于梯度小波纹理模型的纹理分割方法能准确地分割图像中不同的纹理区域。
在研究中我们还发现边缘检测方法适用于图像比较复杂但是受噪声影响较小的
图像，而纹理图像分割方法更适用于图像结构简单但是受噪声影响严重的图像。
ABSTRACT
Left ventricular (LV) volume measurement is a typical application of ultrasound
medical image segmentation. Blurred edges in echocardiograms make the
measurement very difficult. Aiming at this application, firstly, noise suppression and
edge detection methods were studied based on wavelet transform, and then, texture
segmentation methods were developed on this basis.
On the basis of assimilating the former achievements, we applied several
theories and methods, such as wavelet transform, fuzzy sets, rough set, Markov
random field, feature space clustering, in ultrasound image processing. The main
innovations and improvements we have made in this study are as follows:
Firstly, the wavelet shrinkage technology was improved, in which the shrinkage
was not processed in the domain of wavelet coefficients but processed in the domain
of wavelet vectors’modulus. In addition, the relationship among the thresholds of
various scales was derived, and a uniform threshold formula was presented.
Secondly, rough set theory and rotating neighborhood technology were used in
the noise suppression. Noise rough set was defined according to condition attribute
we defined. The upper approximation and the lower approximation set were
separately used to suppress noise. An isolated point noise suppression method, an
edge detection method, and a region edge detection method based on rough set and
rotating neighborhood technology were developed and applied in the texture
segmentation after processing.
Thirdly, a wavelet fuzzy operator edge detection method was proposed. In this
method, wavelet multiscale edge detection and fuzzy edge detection were combined,
multiscale edges, being the results of wavelet multiscale edge detection, became the
object of fuzzy processing. A fuzzy membership matrix (fuzzy plane) was constructed
by defining a discrete membership function to image edge set. A fuzzy enhancement
operator with changeable crossover point was applied in the enhancement of the
fuzzy plane to get a certain image edge set. This method took the advantages of
multiscale of wavelet transform and ability to cope with uncertain problems of fuzzy
sets; as a result, it resolved the conflict between localization and detection in edge
detection.
Fourthly, a gradient wavelet texture model was presented based on Gauss
III
ABSTRACT
Markov random field and gradient wavelet transform. The parameters of the model
forms a multiscale texture feature space, and provided a multiscale description of
image texture. K-means algorithm was applied in the clustering of the parameters,
and in the process of clustering the result of coarser scales acted as the initial
clustering center of the finer scales, as a result, the efficiency of clustering was
improved. This method took the advantages of Markov random field image model
and imported the multiscale feature of wavelet transform.
In this dissertation objective evaluation methods were adopted. The result of
evaluationindicated that the wavelet shrinkage and noise suppressionbased on rough
set could suppress speckle noise in ultrasound images effectively, and the wavelet
fuzzy operator edge detection method had a good detection and noise-attenuating
ability, and the texture segmentation based on the gradient wavelet texture model
could give an exact segmentation of areas with different texture. In addition, we
found that edge detection methods were accomplished in the processing of images
with complex structure and light noise, on the contrary, texture segmentation methods
were accomplished in the processing of images with simple structure and severe
noise.
超声心动图的心室容积测量是超声医学图像分割技术的典型应用；图像边
缘模糊给心室容积测量的实践带来了很大的困难。本研究从这一典型应用出发，
首先以小波变换理论为基础进行了超声医学图像噪声抑制及边缘检测方法的研
究，接着在此基础上开展了基于纹理的图像分割方法的研究。
本文在吸收前人成果和分析研究的基础上将小波变换、模糊集、粗糙集、
马尔可夫随机场、特征空间聚类等理论和方法应用于超声医学图像处理，以此
为基础提出了几种组合方法并对一些方法进行了改进。这些组合方法和改进的
方法在超声医学图像处理实验中取得了满意的效果。
本论文的主要创新表现在以下方面：
改进了小波收缩噪声抑制技术，将在小波系数域进行的收缩改进到小波矢
量模值域上进行；根据统计知识和李氏指数的理论推导出了各个阶次噪声抑制
阈值统一公式。
将粗糙集理论和旋转邻域技术应用于超声医学图像噪声抑制，通过定义噪
声集合的条件属性集定义了噪声粗糙集，并分别利用上逼近集合和下逼近集合
对图像进行了噪声抑制处理；在基于粗糙集的噪声抑制基础上提出了基于粗糙
集的孤立点抑制方法，基于粗糙集的边缘提取方法和基于粗糙集的区域边缘提
取方法，并利用这些方法对纹理分割后的图像进行了处理。
将小波变换多尺度边缘检测和模糊边缘检测方法有机的结合起来，提出了
小波模糊算子边缘检测方法；将小波变换边缘检测的多尺度检测结果作为模糊
集处理的对象，以离散形式给出了多尺度边缘对图像边缘集合的多变量模糊隶
属度函数，构成边缘集合的模糊隶属度矩阵（模糊特征平面）；采用分界点可调
的模糊增强算子对模糊隶属度矩阵进行增强以获得最终的边缘检测结果。小波
模糊算子边缘检测方法通过把小波变换的多尺度特性和模糊集善于处理不确定
性问题的优点结合起来，有效了解决了精确定位和有效检出的矛盾。
以马尔可夫随机过程和梯度小波变换为基础提出了梯度小波纹理模型；多
尺度的梯度小波纹理模型参数形成一个多尺度纹理特征空间，采用特征空间聚
类方法可以实现超声医学图像的纹理分割；我们在聚类过程中将较大尺度的聚
类结果作为较小尺度的聚类初始值提高了聚类过程的效率。梯度小波纹理模型
利用了马尔可夫随机场图像模型的优点和基于该模型的成熟方法，并且引入多
尺度、多分辨率特性。
本文通过客观评价方法对本文使用的图像处理方法进行了评价。评价结果
I
中文摘要
显示小波收缩噪声抑制技术和基于粗糙集的噪声抑制技术能有效地抑制图像中
的散斑噪声，小波模糊算子边缘检测方法有良好的边缘提取能力和抗噪声性能，
基于梯度小波纹理模型的纹理分割方法能准确地分割图像中不同的纹理区域。
在研究中我们还发现边缘检测方法适用于图像比较复杂但是受噪声影响较小的
图像，而纹理图像分割方法更适用于图像结构简单但是受噪声影响严重的图像。
ABSTRACT
Left ventricular (LV) volume measurement is a typical application of ultrasound
medical image segmentation. Blurred edges in echocardiograms make the
measurement very difficult. Aiming at this application, firstly, noise suppression and
edge detection methods were studied based on wavelet transform, and then, texture
segmentation methods were developed on this basis.
On the basis of assimilating the former achievements, we applied several
theories and methods, such as wavelet transform, fuzzy sets, rough set, Markov
random field, feature space clustering, in ultrasound image processing. The main
innovations and improvements we have made in this study are as follows:
Firstly, the wavelet shrinkage technology was improved, in which the shrinkage
was not processed in the domain of wavelet coefficients but processed in the domain
of wavelet vectors’modulus. In addition, the relationship among the thresholds of
various scales was derived, and a uniform threshold formula was presented.
Secondly, rough set theory and rotating neighborhood technology were used in
the noise suppression. Noise rough set was defined according to condition attribute
we defined. The upper approximation and the lower approximation set were
separately used to suppress noise. An isolated point noise suppression method, an
edge detection method, and a region edge detection method based on rough set and
rotating neighborhood technology were developed and applied in the texture
segmentation after processing.
Thirdly, a wavelet fuzzy operator edge detection method was proposed. In this
method, wavelet multiscale edge detection and fuzzy edge detection were combined,
multiscale edges, being the results of wavelet multiscale edge detection, became the
object of fuzzy processing. A fuzzy membership matrix (fuzzy plane) was constructed
by defining a discrete membership function to image edge set. A fuzzy enhancement
operator with changeable crossover point was applied in the enhancement of the
fuzzy plane to get a certain image edge set. This method took the advantages of
multiscale of wavelet transform and ability to cope with uncertain problems of fuzzy
sets; as a result, it resolved the conflict between localization and detection in edge
detection.
Fourthly, a gradient wavelet texture model was presented based on Gauss
III
ABSTRACT
Markov random field and gradient wavelet transform. The parameters of the model
forms a multiscale texture feature space, and provided a multiscale description of
image texture. K-means algorithm was applied in the clustering of the parameters,
and in the process of clustering the result of coarser scales acted as the initial
clustering center of the finer scales, as a result, the efficiency of clustering was
improved. This method took the advantages of Markov random field image model
and imported the multiscale feature of wavelet transform.
In this dissertation objective evaluation methods were adopted. The result of
evaluationindicated that the wavelet shrinkage and noise suppressionbased on rough
set could suppress speckle noise in ultrasound images effectively, and the wavelet
fuzzy operator edge detection method had a good detection and noise-attenuating
ability, and the texture segmentation based on the gradient wavelet texture model
could give an exact segmentation of areas with different texture. In addition, we
found that edge detection methods were accomplished in the processing of images
with complex structure and light noise, on the contrary, texture segmentation methods
were accomplished in the processing of images with simple structure and severe
noise.
引文
参考文献
1．李卫萍，秦永文，赵仙先等，超声心动图在室间隔缺损经导管封堵术中的应
用价值，中华超声医学影像杂志，2002，11（11）：645-647
2．柳建华，张青萍，周玉清等，经静脉注射新型声学造影剂和三维超声观察兔
VX2 肝癌的实验研究,中华超声影像学杂志，2001，10（4）：244-246
3．Aleksandra Mojsilovi′c,* Miodrag Popovi c, Characterization of Visually Similar
Diffuse Diseases from B-Scan Liver Images Using Nonseparable Wavelet
Transform, IEEE Trans. onMedical Imaging, 1998, 17(4): 541-549
4．王佳棣，诊断超声的图像处理技术，中国医疗器械杂志，2002，26（5）：377
5．GE Medical Systems 产品介绍，http://www.gemedicalsystems.com/rad/us/
6．RenéG.Aarnink, Jean J.M.C.H. de la Rosette, Wouter F.J. Feitz, et.al, A
preprocessing algorithm for edge detection with multiple scales of resolution,
European Journal of Ultrasound, 1997, 5(2): 113-126
7．Duncan J.S, Ayache N., Medial image analysis: Progress over two decades and the
challenges ahead, IEEE Trans on Pattern Anal. & Mach. Imtell., 2000, 22(1):
181-204
8．S.D. Olabarriaga, A.W.M. Smeulders, Interaction in the segmentation of medical
images:Asurvey, MedicalImageAnalysis, 2001, 5(2): 127–142
9．Pal N. R., Pal S. K., A review on image segmentation techiques, Pattern Recogni-
tion, 1993, 26(9): 1277 -1294
10．C．Delgorge, P. Vieyres, G. Poisson, C. Rosenberger, et.al, Comparative survey of
ultrasound images compression methods dedicated to a tele-echography robotic
system, Engineering in Medicine and Biology Society, 2001. Proceedings of the
23rd Annual International Conference of the IEEE , 2001, 3: 2461 -2464
11．Yung-GiWu, Medical image compression by sampling DCT coefficients, IEEE
Transactions onInformation Technology in Biomedicine,2002, 6(1): 86-94
12．B. M. Dawant, Non-rigid registration pf medical images: purpose and methods, a
short survey, 2002 IEEE International Symposium on Biomedical Imaging, 2002,
465-468
13．M. Unser, A. Aldroubi, A review of wavelets in biomedical applications,
Proceedings of IEEE, 1996, 84(4): 626-638
14．A. F. Frangi, W. J. Niessen, M. A. Viergever, Tree-dimensional modeling for
functional analysis of cardiac images, a review, IEEE Trans on Medical Imaging,
2001, 20(1): 2-5
15．应伟雯，鲁红，宋伊丽，子宫的三维超声成像，中华超声影像学杂志，2001，
10（4）：223-224
16．邢占峰，吕扬生，关红彦等，基于小波变换的 B 超图像噪声消除和边缘检
测，电子测量与仪器学报，2000，14（增）：638-641
95
参考文献
17．J. Liu, J. B. Weaver, D.M. Healy, etc., Noise reduction with a multiscale edge
representation and perceptual criteria, Proceedings of the IEEE-SPInternational
Symposium Time-Frequency and Time-ScaleAnalysis, 1992, 555-558
18．Zhong Hua, Man-Nang Chong, A wavelet-denoising approach for removing
background noise in medical images, Proceedings of 1997 International
Conference onInformation, Communications and Signal Processing, 1997, 2:
980-983
19．H.Guo, J.E.Odegard, M.Lang, etc, “Wavelet based speckle reduction with applica-
tion to SAR based ATD/R,”in Proc.ICIP, 1994, 1(1):75-79.
20．刘建峰 戚飞虎，一种基于子波变换得图像边缘提取及去噪方法，红外与毫
米波学报，1997，Vol.16(10)351-356
21．Xuli Zong，Andrew F. Kaine, and Edward A. Geiser, Speckle Reduction and
Contrast Enhancement of Echocardiograms via Multiscale Nonlinear Processing,
IEEE trans. Med. Imag.,1998, vol. 17( 4):532-540
22．Young-Won Song, S.S. Upda,A new morphological approach for reducing
speckle noise in ultrasonic images, IEEE 39th Midwest symposium onCircuits
and Systems, 1996, 3:1397-1400
23．P. Maragos and R.W. Schafer, Morphological filters Part I: Their set theoretic
analysis and realtions to linear shift invariant filters, IEEE trans. On Accoust.,
Speech, Signal Processing, 1987, 2(8): 1153-1169
24．P. Maragos and R.W. Schafer, Morphological filters Part II: Their set theoretic
analysis and realtions to linear shift invariant filters, IEEE trans. On Accoust.,
Speech, Signal Processing, 1987, 2(8): 1170-1184
25．A. Kher and S. Mitra, Optimum morphological filtering to remove speckle noise
form SAR images, Nonlinear Image Processing, SPIE, 1993, 2030:97-107
26．于起峰，孙祥一，用曲线大窗口平滑散斑条纹图的方法研究，力学学报，
2002，34(3): 458-462
27．Lee J.S., Speckle analysis and smoothing of Synthetic Aperture Radar images,
Computer graphics and images processing, 1981, 17(1): 24-32
28．M. Kunt, Edge detection:a tuttorial review, IEEE International Conference on
Acoustics, Speech, and Signal Processing(ICASSP’82), 1982, 7:1172-1175
29．阮秋琦编著，数字图像处理学，电子工业出版社，2001，199-233，429-480
30．袁华，滕奇志，边缘检测及其在医学图像中的应用，生物医学工程学杂志，
2001，18（1）：149-153
31．J. Canny, A computational approach to edge detection, IEEE Trans. Pattern Anal.
Machine Intell., 1986, 8(6):679–698
32．Pal S.K., King R.A. On edge detection of X-ray images using fuzzy sets, IEEE
Trans. Patt. Anal. and Machine Intell. 1983, 5(1):69-77
33．Stephane Mallat and Sifen Zhong, Charaterization of siganals from multiscale
edges, IEEE Trans. Patt.Anal. and Mach. Intell. 1992, 14(7): 710-732
96
参考文献
34．Chao C. H., Dhawan A. P., Edge detection using a Hopfield neural network,
Optical Engineering, 1994, 33: 3739-3747
35．熊联欢，胡汉平，李德华等，用 BP 网络进行彩色图像分割和边缘检测，华
中理工大学学报，1999，27(2): 87-89
36．杨海军，梁德群，一种新的基于信息测度和神经网络的边缘检测方法 ，电
子学报，2001，29(1): 51-53
37．Tim Mclnerney, Demetri Terzopoulos, Deformable models in medical image
analysis: a survey, Medical Image Analysis, 1996, 1(2): 91-108
38．Kass M. Wirkin A, Terzopoulos D., Snakes: active contour models, International
Journal of Computer Vision, 1988, 1(4): 321-331
39．章毓晋，图象分割，科学出版社，2001，43-66，122-135，149-182
40．Zhang Y. J., Gerbrands J. J., Transition region determination based thresholding,
Pattern Recognition Letters, 1991, 12: 13-23
41．Nakagawa Y., Rosenfeld A., Some experiments on variable thresholding, Pattern
Recognition, 1979, 11: 191-204
42．Lee C., Hun S., Ketter T.A. etc, Unsupervised connectivitybased thresholding
segmentation of midsaggital brain MR images, Computers in Biology and
Medicine, 1998, 28(3): 309-228
43．Pun T., A new method for gray-level picture thresholding using the entropyof the
histogram, Signal Processing, 1980, 2(3): 233-237
44．杨加，吴祈耀，田捷等，几种图像分割算法在 CT 图像分割上的实现和比较，
北京理工大学学报，2002，20(6): 720-724
45．WanS.Y., Higgins W. E., Symmetric Region Growing, Proc of the International
IEEE conference on Image Processing，Vancouver Canada, 2000, 96-99
46．屈彬，王景熙，郑昌琼等，一种基于区域生长规则的快速边缘跟踪算法，
四川大学学报（ 工程科学版），2002，34(2)：100-103
47．Manousakes I. N., Undrill P. E., Gameron G. G.. etc, Split-and-merge segmenta-
tion of magnetic resonance images: performance evaluation and extension to
three dimensions, Computers and Biomedical Research, 1998, 31(6): 393-412
48．赵锋，赵荣椿，分裂-合并方法在图象分割、目标提取中的应用，西北工业
大学学报，2000，18(1): 116-120
49．Wells W., Grimson W., Kikins R. etc, Adaptive segmentation of MRI data, IEEE
Trans on Medical Imaging, 1996, 15(4): 429-442
50．韩逢庆，李红梅，黄席樾，基于遗传算法的一种 c-均值聚类算法研究，计
算机工程与应用，2000，38(24): 64-65
51．吴颖谦，施鹏飞，基于改进演化策略的图像 FCM 聚类分割方法，红外与激
光工程，2002，31(6): 478-481
52．王兴伟，沈兰荪，卫保国，基于改进的 k-均值聚类和数学形态学的彩色眼
科图像病灶分割，生物医学工程学报，2002，21(5): 443-448
97
参考文献
53．刘正云,鲍旭东,舒中力等，模糊 kohonen聚类网络用于骨髓细胞图像分割，
东南大学学报（ 自然科学版），2002，32(6): 1-4
54．Geman S. and Geman D., Stochastic Relaxation, Gibbs distributions, and the
Bayesian restoration of images, IEEE Trans on Patt.Anal.And Mach. Intell.,
1984,6(6): 721-741
55．Park, Jaehyun and Kurz, Ludwik, Unsupervised segmentation of textured images,
Information Sciences, 1996, 92(1-4): 255-276
56．X. Yang and J. Liu, Unsupervised texture segmentation with one step mean shift
and boundary markov random fields, Pattern Recognition Letters, 2001, 22:
1073-1081.
57．M.N. Shirazi et al., Texture classification based on Markov modeling in wavelet
feature space, Image and Vision Computing, 2000, 18(12): 967–973
58．G. Fan and X.-G. Xia, Maximum likelihood texture analysis and classification
using wavelet-domain hidden Markov model, Conference Record of the
Asilomar Conference on Signals, Systems and Computers, 2000 , 2: 921 -925
59．刘国庆，熊红，基于小波变换和马尔可夫随机场的极化 SAR 图像自动分类，
电子科学学刊，2000，22(3): 359-365
60．李艳，彭嘉雄，基于分维特征的目标分割与检测，华中理工大学学报，2000，
28(8): 1-5
61．刘长征，周大海，γ 刀定位中的 SPECT 图像的自动处理方法研究，哈尔滨
工程大学学报，2002，23(1): 72-75
62．张坤华，王敬儒，张启衡，复杂背景下扩展目标的分割算法研究，红外与
毫米波学报，2002，21(3): 233-237
63．Haralick R. M., Statistical and structural approaches to texture, Proceeding of
IEEE, 1979, 67(5): 786-804
64．Chen D., Wang L., Texture features based on texture spectrum, Pattern Recogni-
tion, 1991, 24: 391-399
65．Chung-mingChen, HenryHorng-shing Lu, and Ko-chung Han，A Textural
approachbased on gabor functions for texture edge detectionin ultrasound
images, Ultrasound in Med. & Biol., 2001, 27( 4): 515–534
66．Mausumi Acharyya, Malay K. Kundu, An adaptive approach to unsupervised
texture segmentationusing M-Band wavelet transform, SignalProcessing 2001,
81:1337-1356
67．Milan Sonka, Vaclav Hlavac, Roger Boyle, 图像处理分析和机器视觉(第二版)，
人民邮电出版社，影印版，2002，35-37，91-93
68．夏德深，傅德胜，现代图像处理技术与应用，东南大学出版社，1997，41-67
69．苗振魁，任长明，医用超声仪器原理及应用，天津大学出版社，1993，137-140
70．A.K.Jain, Fundamentals of Digital Image Processing, Englewood Cliffs, NJ:
Printice-Hall, 1989, 313-316
98
参考文献
71．A. Pesavento, H. Ermert, E. Broll Zeitvogel, etc，Highresolutionimagingof
generalized K-distribution parameters using maximum likelihood estimation for
ultrasonic diagnosis of muscle after back surgery, Proceedings of the 1998
International Ultrasonics Symposium, 1998, 2: 1353-1356
72．J.G.Abbott and F.L. Thurstone, Acoustic Speckle: Theory and experimental
analysis, Ultrasound Image., 1979，(1):303-324
73．Lee Jon- Sen, Speckle suppression and analysis of SAR images, Optical
Enineering, 1986, 25(5): 636-643
74．F Safa, G Fiouzar, Speckle removel based on mathematic morphology,Signal
Processing, 1989, 16(4): 320-333
75．Vidakovic B, Lozoya C. B., On time –dependent wavelet denoising, IEEE Trans.
Signal Processing, 1998, 46(9): 2549-2551
76．Donoho, D.L., De-noising by soft-thresholding, IEEE Trans. on Information
Theory, 1995, 41(3): 613-627
77．杨福生，小波变换的工程分析与应用，科学出版社，1999，134-139，145-177
78．S. Mallat, and WenL Huang, Singularity detection and processing with wavelets.
IEEE Trans. InformationTheory, 1992, 38(2): 617-643
79．Chambolle, A.; Lucier, B.J.，Interpreting translation-invariant wavelet shrinkage
as a new image smoothing scale space，IEEE Trans Image Process，2001，10(7):
993-1000
80．刘刚，屈梁生，自适应阈值选择和小波消噪方法研究，信号处理，2002，
18(6): 509-512
81．BinLiu,YuanyuanWang , WeiqiWang, Spectrogram enhancement algorithm: a
soft thresholding-based approach, Ultrasound in Med. & Biol., 1999, 25(5):
839-846
82．王建平，王志红，王金玲，小波分析在图像消噪中的应用研究，微电子学
与计算机，2002，8: 22-24
83．Shark L.K., Yu C., Denoising by optimal fuzzy thresholding in wavelet domain,
Electronics Letters, 2000, 36(6): 581-582
84．张海澜，王蜀楚，应崇福，B 超图像的斑纹噪声和人体软组织的随机特性，
应用声学，1991，10(6): 35-42
85．高世泽，几种概率分布的特征和稳定性，重庆师范学院学报(自然科学版)，
1990，7(2): 31-40
86．邢占峰，基于小波变换的 B 超图像噪声抑制边缘提取及图像增强，[硕士学
位论文]，天津，天津大学，2001
87．Pawlak, “Rough Sets”, International Journal of Information and Computer
Sciences, 1982, 11: 341-356
88．Z. M. Wojicik, “Rough Approximation of Shapes in Pattern Recognition”,
Computer Vision, 1987, Graphics and Image Processing, 40: 228-249
99
参考文献
89．Zbigniew M. Wojicik, Application of Rrough Sets for Edge Enhancing Image
Filters, IEEE International Conference on Image Processing 1 Nov 13-16 1994
1994 sponsored by: IEEE IEEE : 525-529.
90．徐立中，王慧斌等，基于粗糙集理论的图像增强方法，仪器仪表学报，2000，
21(5):514-524
91．李男，邱天爽等，基于粗糙集的数据挖掘技术及其在临床医学诊断中的应
用，上海生物医学工程，第 23 卷第 2 期，pp3-7，2000 年.
92．胡静，曹先彬等，基于相容粗糙集的图形图像信息预检索，计算机辅助设
计与图形学学报，第 14 卷第 3 期，pp242-246，2000 年 3 月.
93．Z. M. Wojicik, A Natural Approach to Image Processing and Pattern Recognition:
Rotating Neighborhood Technique, Self-Adapting Threshold, Segmentation and
Shape Recognition, 1985, Pattern Recognition, 18(5): 299-326
94．唐正军，刘代志，改进多尺度 CANNY 算子在 SAR 图像边缘提取中的应用，
上海航天，2000，17(2): 7-10
95．刘曙光，刘明远，何钺，基于 Canny 准则的基数 B 样条小波边缘检测，信
号处理，2001，11(5): 418-423
96．杨烜，梁德群，杨万海，边缘检测中 Canny 算子、二次样条小波算子性能
分析，通信学报，1999，20(8): 47-51
97．解梅，马征，B 样条小波边缘检测算子的应用研究，电子学报，1999，27(1):
106-108
98．杨正远，郑建宏，小波在图象边缘检测中的应用，重庆邮电学院学报，1997，
9(1): 5-9
99．杨亚军，张红林，李言俊等，基于小波算子的图像边缘检测，弹箭与制导
学报，1998，4: 7-11
100．蔡靖，刘峰，丁润涛，模糊迭代边缘检测器，电子与信息学报，2001，23(2):
134-139
100．S.K. Pal, R.A. King, On edge detection of X-ray images using fuzzy sets, IEEE
Trans. On Patt. Anal.&Mach. Intel., 1983, 5(1): 69-77
101．Wang Hui, Multi-gray edge detection based on generalized fuzzy set, Journal of
Electronics, 2002, 19(4): 426-430
102．陈武凡，谢新朋，洪文松，广义模糊集合论及其在图像处理中的新应用，
生物医学工程学报，1999，18(1):66-73
103．熊兴华，李新涛，面向对象的遥感影像模糊增强，武汉大学学报·信息科
学版，2002，27(5): 516-521
104．S.K.Setarehdan, and J.J.Soraghan, Cardiac left ventricular volume changes
assessment by long axis echocardiographical image processing, IEE
Proceedings- Vision, Image and Signal Processing, 1998, 145(3): 203-212
105．S.K.Setarehdan, and J.J.Soraghan, Fuzzy Multiscale Edge Detection(FMED)
Applied to Autonetic LeftVebtricle Boundary Extraction, Image Processing and
100
参考文献
Its Applications, 1999. Seventh International Conference on (Conf. Publ. No.
465) , 1999, 2: 552-556.
１０６．S.K.Setarehdan, and J.J.Soraghan, AutomaticCardiacLVBoundaryDetection
and Tracking Using Hybrid Fuzzy Temporal and Fuzzy Multiscale Edge
Detection, IEEE Transactions on Biomedical Engineering, 1999, 46(11):
1364-1376.
107．C.Vertan, A.stoica, C.Fernandez-Maloigne, Perceptual Fuzzy Multiscale Color
Edge Detection, Fuzzy Systems, 2001, The 10th IEEE International Conference
on , 2001, 1: 19-22
１０８．边肇祺 编著，《模式识别》（第二版），清华大学出版社，2000，273-283
109．周峰，纹理分析中若干问题的研究：[博士学位论文]，2001，北京，北京
大学，2001: 1-10
110．吴高洪，章毓晋，林行刚，分割双纹理图像的最佳 Gabor 滤波器设计方法，
电子学报，2001，29(1): 48-50
111．郭立，朱俊株，陆大虎，基于 Gabor 小波变换的无监督纹理图像分割，微
机发展，2000，5: 51-54
112．吴高洪，章毓晋，林行刚，利用小波变换和特征加权进行纹理分割，中国
图象图形学报，2001，6(A)(4):333-337
113．胡召玲，郭达志，盛业华，基于小波分解的星载 SAR 图像纹理信息提取，
遥感学报，2001，5(6): 423-427
114．杨浩，裴继红，杨烜，基于小波框架分解和模糊软聚类的纹理图像分割方
法，西安工业学院学报，1999，19(2): 103-108
115．叶桦，章国宝，陈维南，基于小波变换的纹理图像分割，东南大学学报，
1999，29(1): 44-48
116．刘昉，赵荣椿，程敬之，提高超声图像纹理分析空间分辨率的研究，中国
生物医学工程学报，2001，20(6): 566-570
117．C.-T. Li, Multiresolution image segmentation integrating Gibbs sampler and
region merging algorithm, Signal Processing, 2003, 83(1): 67-78
118．S. Stan, G. Palubinskas, M. Datcu, Bayesian selection of the neighbourhood
order for Gauss-Markov texture models, Pattern Recognition Letters, 2002,
23(10): 1229-1238
119．郭英凯，杨杰，陆正刚，基于高斯-马尔可夫随机场和神经网络的无监督纹
理分割，红外与激光激光工程，2000，29(2): 5-8
120．杨绍国，尹忠科，罗炳伟，分形多尺度分离图像分割，模式识别与人工智
能，1998，11(3): 347-351
121．郭立，陆大虎，朱俊株，基于 Gabor 多通道滤波和 Hopfield 神经网络的纹
理图象分割，计算机工程与应用，2000，36(6): 39-41
122．郑肇葆，郑宏，潘励，纹理分类中遗传算法参数的选择，测绘学报，2000，
29(1): 35-39
101
参考文献
123．郑肇葆，郑宏，基于遗传算法的影像纹理分类，武汉测绘科技大学学报，
1998，23(4): 337-339
124．郑肇葆，郑宏，用遗传算法确定马尔柯夫随机场的最佳参数，武汉测绘科
技大学学报，2000，25(3): 221-225
125．马永军，方凯，方廷健，基于支持向量机和距离度量的纹理分类，中国图
象图形学报，2002，7(A)(11): 1151-1155
126．刘伟强，支持向量机载图像处理应用中若干问题研究，[硕士学位论文]，
南京，南京理工大学，2002
127．Michael S. Landy, Visual Perception of Texture, http://www.cns.nyu.edu/~msl/
texentry2.pdf
128．郦苏丹，张翠，王正志，基于马尔可夫随机场的 SAR 图象目标分割，中国
图象图形学报，2002，7(A)(8):794-799
129．J. E. Besag, Spatial interaction and the statistical analysis of lattice systems, J.
Roy. Statist. Soc. Ser. B B-36:192-235(1974).
130．J. W. Woods, Two-dimensional discrete Markovian fields, IEEE Transactions on
Information Theory, 1972, 18(2): 232-240
131．J. W. Woods, Correction to 'Two-Dimensional Discrete Markovian Fields', IEEE
Transactions on Information Theory, 1972, 18(4): 541-541
132．J. E. Besag, Efficiency of pseudo-likelihood estimates for simple Gaussian
fields, Biometrika, 1977, 64:616-618
133．S. Lakshmanan,H.Derin, Simultaneous parameter estimation and segmentation
of Gibbs random fields using simulated annealing, IEEE Trans. on Patt. Anal.
& Mach. Intel. , 1989, 11(8): 799-813
134．Mallat, S.G., A theory for multiresolution signal decomposition: the wavelet
representation. IEEE Trans. PatternAnal. Mach. Intell., 1989, 11(7): 674-693
135．Chang, T., Kuo, C.C.J., Texture analysis and classificationwith tree-structured
wavelet transform. IEEE Trans. on Image Process, 1993, 2 (4):429-447
136．Laine, A., Fan, J., Texture classifiation by wavelet packet signatures. IEEE
Trans. on PatternAnal. Mach. Intell., 1993, 15 (11):1186-1191
137．Unser, M., Texture classification and segmentation using wavelet frames. IEEE
Trans. Image Process., 1995, 4 (11), 1549-1560
138．Jing-Wein Wang, Chin-Hsing Chen , Wei-Ming Chien, Textureclassification
using non-separable two-dimensional wavelets，Pattern Recognition Letters，
1998, 19(13): 1225-1234
139．Laws K L., Rapid texture identification, SPIE, 1980, 238:376-380.
140．马作民，毛士艺，刘样林，SAR 图像非平稳性对图像模型和滤波降噪方法
的影响，北京航空航天大学学报，2001，27(6): 713-716
141．丁艺芳，基于小波变换和视觉系统的图像质量综合评价新算法，[博士学位
论文]，上海：上海交通大学，2001
102
参考文献
142．杜培军，RADARSAT 图象滤波的研究，中国矿业大学学报，2002，31(2):
132-137
143．李向吉，丁润涛，蔡靖，边缘检测器性能的客观定量评价，1999，21(5):
634-639
144．侯格贤，毕笃彦，吴成柯，图象分割质量评价方法研究，中国图象图形学
报，2000，5(A)(1):39-43
145．王爱民，沈兰荪，图像分割研究综述，测控技术，2000，19(5): 1-7
146．Zhang.Y J.,A survey on evaluation methods for image segmentation, Pattern
Recognition, 1996, 29(8): 1335-1346
147．Sahoo P K, Soltani S., Wong A.K.C., etc, Survey of thresholding techniques,
Comput Vision Graphics Image Process, 1988, 41(2): 233-260
148．Straters K., Gerbrands J.J., Three-dimensional image segmentation using a split,
merge and group approach, Pattern Recognition Letters, 1991, 24(12): 307-325
149．Abdou Ikram E., Pratt William K., Quantitative design and evaluationof
enhancement/thresholding edge detectors, Proc IEEE, 1979, 67(5): 753-763
150．Zhang Y. J., Gerbrands J.J., Objective and quantitative segmentation evaluation
and comparison, Signal Processing, 1994, 39(1-2): 43-54
151．A. Achim, A. Bezerianos, P. Tsakalides, Ultrasound image denoising via maxi-
mum a posteriori estimation of wavelet coefficients, Engineering in Medicine
and Biology Society, 2001. Proceedings of the 23rd Annual International Con-
ference of the IEEE, 2001, 3:2553 -2556
152．秦石成，秦兆冰等，心脏及血管功能的超声评价，郑州：郑州大学出版社，
2001，36-38
153．Hiroyuki Yoshida, Bilgin Keserci, David D. Casalino. Etc, Segmentation of liver
tumors in ultrasound images based on scale-space analysis of continuous
wavelet transform, Proc IEEE Ultrason Symp, 1998, 2:1713-1716
154．R. Ravhon, D. Adam, L. Zelmanovitch, Validation of Ultrasonic Image
Boundary RecognitioninAbdominalAorticAneurysm, IEEE Transactions on
medical imaging, 2001, 20(8): 751-763
155．Consolatina Liguori, Alfredo Paolillo,Antonio Pietrosanto, An Automatic Mea-
surement System for the Evaluation of Carotid Intima-Media Thickness,IEEE
Tans. on Instramentation and Measurement, 2001, 50(6): 1684-1691
156．Chung-Ming Wu, Yung-Chang Chen,Kai-Sheng Hsieh, Texture features for
classification of ultrasonic liver images, IEEE Trans onMedical Imaging, 1992,
11(2): 141-152
157．A.V. Oppenheim, R.W. Schafer, T.R. Buck, Discrete-TimeSignalProcessing
(Second Edtion)（离散时间信号处理，刘树堂，黄建国译），西安交通大学
出版社，2001，9，131-134
1．李卫萍，秦永文，赵仙先等，超声心动图在室间隔缺损经导管封堵术中的应
用价值，中华超声医学影像杂志，2002，11（11）：645-647
2．柳建华，张青萍，周玉清等，经静脉注射新型声学造影剂和三维超声观察兔
VX2 肝癌的实验研究,中华超声影像学杂志，2001，10（4）：244-246
3．Aleksandra Mojsilovi′c,* Miodrag Popovi c, Characterization of Visually Similar
Diffuse Diseases from B-Scan Liver Images Using Nonseparable Wavelet
Transform, IEEE Trans. onMedical Imaging, 1998, 17(4): 541-549
4．王佳棣，诊断超声的图像处理技术，中国医疗器械杂志，2002，26（5）：377
5．GE Medical Systems 产品介绍，http://www.gemedicalsystems.com/rad/us/
6．RenéG.Aarnink, Jean J.M.C.H. de la Rosette, Wouter F.J. Feitz, et.al, A
preprocessing algorithm for edge detection with multiple scales of resolution,
European Journal of Ultrasound, 1997, 5(2): 113-126
7．Duncan J.S, Ayache N., Medial image analysis: Progress over two decades and the
challenges ahead, IEEE Trans on Pattern Anal. & Mach. Imtell., 2000, 22(1):
181-204
8．S.D. Olabarriaga, A.W.M. Smeulders, Interaction in the segmentation of medical
images:Asurvey, MedicalImageAnalysis, 2001, 5(2): 127–142
9．Pal N. R., Pal S. K., A review on image segmentation techiques, Pattern Recogni-
tion, 1993, 26(9): 1277 -1294
10．C．Delgorge, P. Vieyres, G. Poisson, C. Rosenberger, et.al, Comparative survey of
ultrasound images compression methods dedicated to a tele-echography robotic
system, Engineering in Medicine and Biology Society, 2001. Proceedings of the
23rd Annual International Conference of the IEEE , 2001, 3: 2461 -2464
11．Yung-GiWu, Medical image compression by sampling DCT coefficients, IEEE
Transactions onInformation Technology in Biomedicine,2002, 6(1): 86-94
12．B. M. Dawant, Non-rigid registration pf medical images: purpose and methods, a
short survey, 2002 IEEE International Symposium on Biomedical Imaging, 2002,
465-468
13．M. Unser, A. Aldroubi, A review of wavelets in biomedical applications,
Proceedings of IEEE, 1996, 84(4): 626-638
14．A. F. Frangi, W. J. Niessen, M. A. Viergever, Tree-dimensional modeling for
functional analysis of cardiac images, a review, IEEE Trans on Medical Imaging,
2001, 20(1): 2-5
15．应伟雯，鲁红，宋伊丽，子宫的三维超声成像，中华超声影像学杂志，2001，
10（4）：223-224
16．邢占峰，吕扬生，关红彦等，基于小波变换的 B 超图像噪声消除和边缘检
测，电子测量与仪器学报，2000，14（增）：638-641
95
参考文献
17．J. Liu, J. B. Weaver, D.M. Healy, etc., Noise reduction with a multiscale edge
representation and perceptual criteria, Proceedings of the IEEE-SPInternational
Symposium Time-Frequency and Time-ScaleAnalysis, 1992, 555-558
18．Zhong Hua, Man-Nang Chong, A wavelet-denoising approach for removing
background noise in medical images, Proceedings of 1997 International
Conference onInformation, Communications and Signal Processing, 1997, 2:
980-983
19．H.Guo, J.E.Odegard, M.Lang, etc, “Wavelet based speckle reduction with applica-
tion to SAR based ATD/R,”in Proc.ICIP, 1994, 1(1):75-79.
20．刘建峰 戚飞虎，一种基于子波变换得图像边缘提取及去噪方法，红外与毫
米波学报，1997，Vol.16(10)351-356
21．Xuli Zong，Andrew F. Kaine, and Edward A. Geiser, Speckle Reduction and
Contrast Enhancement of Echocardiograms via Multiscale Nonlinear Processing,
IEEE trans. Med. Imag.,1998, vol. 17( 4):532-540
22．Young-Won Song, S.S. Upda,A new morphological approach for reducing
speckle noise in ultrasonic images, IEEE 39th Midwest symposium onCircuits
and Systems, 1996, 3:1397-1400
23．P. Maragos and R.W. Schafer, Morphological filters Part I: Their set theoretic
analysis and realtions to linear shift invariant filters, IEEE trans. On Accoust.,
Speech, Signal Processing, 1987, 2(8): 1153-1169
24．P. Maragos and R.W. Schafer, Morphological filters Part II: Their set theoretic
analysis and realtions to linear shift invariant filters, IEEE trans. On Accoust.,
Speech, Signal Processing, 1987, 2(8): 1170-1184
25．A. Kher and S. Mitra, Optimum morphological filtering to remove speckle noise
form SAR images, Nonlinear Image Processing, SPIE, 1993, 2030:97-107
26．于起峰，孙祥一，用曲线大窗口平滑散斑条纹图的方法研究，力学学报，
2002，34(3): 458-462
27．Lee J.S., Speckle analysis and smoothing of Synthetic Aperture Radar images,
Computer graphics and images processing, 1981, 17(1): 24-32
28．M. Kunt, Edge detection:a tuttorial review, IEEE International Conference on
Acoustics, Speech, and Signal Processing(ICASSP’82), 1982, 7:1172-1175
29．阮秋琦编著，数字图像处理学，电子工业出版社，2001，199-233，429-480
30．袁华，滕奇志，边缘检测及其在医学图像中的应用，生物医学工程学杂志，
2001，18（1）：149-153
31．J. Canny, A computational approach to edge detection, IEEE Trans. Pattern Anal.
Machine Intell., 1986, 8(6):679–698
32．Pal S.K., King R.A. On edge detection of X-ray images using fuzzy sets, IEEE
Trans. Patt. Anal. and Machine Intell. 1983, 5(1):69-77
33．Stephane Mallat and Sifen Zhong, Charaterization of siganals from multiscale
edges, IEEE Trans. Patt.Anal. and Mach. Intell. 1992, 14(7): 710-732
96
参考文献
34．Chao C. H., Dhawan A. P., Edge detection using a Hopfield neural network,
Optical Engineering, 1994, 33: 3739-3747
35．熊联欢，胡汉平，李德华等，用 BP 网络进行彩色图像分割和边缘检测，华
中理工大学学报，1999，27(2): 87-89
36．杨海军，梁德群，一种新的基于信息测度和神经网络的边缘检测方法 ，电
子学报，2001，29(1): 51-53
37．Tim Mclnerney, Demetri Terzopoulos, Deformable models in medical image
analysis: a survey, Medical Image Analysis, 1996, 1(2): 91-108
38．Kass M. Wirkin A, Terzopoulos D., Snakes: active contour models, International
Journal of Computer Vision, 1988, 1(4): 321-331
39．章毓晋，图象分割，科学出版社，2001，43-66，122-135，149-182
40．Zhang Y. J., Gerbrands J. J., Transition region determination based thresholding,
Pattern Recognition Letters, 1991, 12: 13-23
41．Nakagawa Y., Rosenfeld A., Some experiments on variable thresholding, Pattern
Recognition, 1979, 11: 191-204
42．Lee C., Hun S., Ketter T.A. etc, Unsupervised connectivitybased thresholding
segmentation of midsaggital brain MR images, Computers in Biology and
Medicine, 1998, 28(3): 309-228
43．Pun T., A new method for gray-level picture thresholding using the entropyof the
histogram, Signal Processing, 1980, 2(3): 233-237
44．杨加，吴祈耀，田捷等，几种图像分割算法在 CT 图像分割上的实现和比较，
北京理工大学学报，2002，20(6): 720-724
45．WanS.Y., Higgins W. E., Symmetric Region Growing, Proc of the International
IEEE conference on Image Processing，Vancouver Canada, 2000, 96-99
46．屈彬，王景熙，郑昌琼等，一种基于区域生长规则的快速边缘跟踪算法，
四川大学学报（ 工程科学版），2002，34(2)：100-103
47．Manousakes I. N., Undrill P. E., Gameron G. G.. etc, Split-and-merge segmenta-
tion of magnetic resonance images: performance evaluation and extension to
three dimensions, Computers and Biomedical Research, 1998, 31(6): 393-412
48．赵锋，赵荣椿，分裂-合并方法在图象分割、目标提取中的应用，西北工业
大学学报，2000，18(1): 116-120
49．Wells W., Grimson W., Kikins R. etc, Adaptive segmentation of MRI data, IEEE
Trans on Medical Imaging, 1996, 15(4): 429-442
50．韩逢庆，李红梅，黄席樾，基于遗传算法的一种 c-均值聚类算法研究，计
算机工程与应用，2000，38(24): 64-65
51．吴颖谦，施鹏飞，基于改进演化策略的图像 FCM 聚类分割方法，红外与激
光工程，2002，31(6): 478-481
52．王兴伟，沈兰荪，卫保国，基于改进的 k-均值聚类和数学形态学的彩色眼
科图像病灶分割，生物医学工程学报，2002，21(5): 443-448
97
参考文献
53．刘正云,鲍旭东,舒中力等，模糊 kohonen聚类网络用于骨髓细胞图像分割，
东南大学学报（ 自然科学版），2002，32(6): 1-4
54．Geman S. and Geman D., Stochastic Relaxation, Gibbs distributions, and the
Bayesian restoration of images, IEEE Trans on Patt.Anal.And Mach. Intell.,
1984,6(6): 721-741
55．Park, Jaehyun and Kurz, Ludwik, Unsupervised segmentation of textured images,
Information Sciences, 1996, 92(1-4): 255-276
56．X. Yang and J. Liu, Unsupervised texture segmentation with one step mean shift
and boundary markov random fields, Pattern Recognition Letters, 2001, 22:
1073-1081.
57．M.N. Shirazi et al., Texture classification based on Markov modeling in wavelet
feature space, Image and Vision Computing, 2000, 18(12): 967–973
58．G. Fan and X.-G. Xia, Maximum likelihood texture analysis and classification
using wavelet-domain hidden Markov model, Conference Record of the
Asilomar Conference on Signals, Systems and Computers, 2000 , 2: 921 -925
59．刘国庆，熊红，基于小波变换和马尔可夫随机场的极化 SAR 图像自动分类，
电子科学学刊，2000，22(3): 359-365
60．李艳，彭嘉雄，基于分维特征的目标分割与检测，华中理工大学学报，2000，
28(8): 1-5
61．刘长征，周大海，γ 刀定位中的 SPECT 图像的自动处理方法研究，哈尔滨
工程大学学报，2002，23(1): 72-75
62．张坤华，王敬儒，张启衡，复杂背景下扩展目标的分割算法研究，红外与
毫米波学报，2002，21(3): 233-237
63．Haralick R. M., Statistical and structural approaches to texture, Proceeding of
IEEE, 1979, 67(5): 786-804
64．Chen D., Wang L., Texture features based on texture spectrum, Pattern Recogni-
tion, 1991, 24: 391-399
65．Chung-mingChen, HenryHorng-shing Lu, and Ko-chung Han，A Textural
approachbased on gabor functions for texture edge detectionin ultrasound
images, Ultrasound in Med. & Biol., 2001, 27( 4): 515–534
66．Mausumi Acharyya, Malay K. Kundu, An adaptive approach to unsupervised
texture segmentationusing M-Band wavelet transform, SignalProcessing 2001,
81:1337-1356
67．Milan Sonka, Vaclav Hlavac, Roger Boyle, 图像处理分析和机器视觉(第二版)，
人民邮电出版社，影印版，2002，35-37，91-93
68．夏德深，傅德胜，现代图像处理技术与应用，东南大学出版社，1997，41-67
69．苗振魁，任长明，医用超声仪器原理及应用，天津大学出版社，1993，137-140
70．A.K.Jain, Fundamentals of Digital Image Processing, Englewood Cliffs, NJ:
Printice-Hall, 1989, 313-316
98
参考文献
71．A. Pesavento, H. Ermert, E. Broll Zeitvogel, etc，Highresolutionimagingof
generalized K-distribution parameters using maximum likelihood estimation for
ultrasonic diagnosis of muscle after back surgery, Proceedings of the 1998
International Ultrasonics Symposium, 1998, 2: 1353-1356
72．J.G.Abbott and F.L. Thurstone, Acoustic Speckle: Theory and experimental
analysis, Ultrasound Image., 1979，(1):303-324
73．Lee Jon- Sen, Speckle suppression and analysis of SAR images, Optical
Enineering, 1986, 25(5): 636-643
74．F Safa, G Fiouzar, Speckle removel based on mathematic morphology,Signal
Processing, 1989, 16(4): 320-333
75．Vidakovic B, Lozoya C. B., On time –dependent wavelet denoising, IEEE Trans.
Signal Processing, 1998, 46(9): 2549-2551
76．Donoho, D.L., De-noising by soft-thresholding, IEEE Trans. on Information
Theory, 1995, 41(3): 613-627
77．杨福生，小波变换的工程分析与应用，科学出版社，1999，134-139，145-177
78．S. Mallat, and WenL Huang, Singularity detection and processing with wavelets.
IEEE Trans. InformationTheory, 1992, 38(2): 617-643
79．Chambolle, A.; Lucier, B.J.，Interpreting translation-invariant wavelet shrinkage
as a new image smoothing scale space，IEEE Trans Image Process，2001，10(7):
993-1000
80．刘刚，屈梁生，自适应阈值选择和小波消噪方法研究，信号处理，2002，
18(6): 509-512
81．BinLiu,YuanyuanWang , WeiqiWang, Spectrogram enhancement algorithm: a
soft thresholding-based approach, Ultrasound in Med. & Biol., 1999, 25(5):
839-846
82．王建平，王志红，王金玲，小波分析在图像消噪中的应用研究，微电子学
与计算机，2002，8: 22-24
83．Shark L.K., Yu C., Denoising by optimal fuzzy thresholding in wavelet domain,
Electronics Letters, 2000, 36(6): 581-582
84．张海澜，王蜀楚，应崇福，B 超图像的斑纹噪声和人体软组织的随机特性，
应用声学，1991，10(6): 35-42
85．高世泽，几种概率分布的特征和稳定性，重庆师范学院学报(自然科学版)，
1990，7(2): 31-40
86．邢占峰，基于小波变换的 B 超图像噪声抑制边缘提取及图像增强，[硕士学
位论文]，天津，天津大学，2001
87．Pawlak, “Rough Sets”, International Journal of Information and Computer
Sciences, 1982, 11: 341-356
88．Z. M. Wojicik, “Rough Approximation of Shapes in Pattern Recognition”,
Computer Vision, 1987, Graphics and Image Processing, 40: 228-249
99
参考文献
89．Zbigniew M. Wojicik, Application of Rrough Sets for Edge Enhancing Image
Filters, IEEE International Conference on Image Processing 1 Nov 13-16 1994
1994 sponsored by: IEEE IEEE : 525-529.
90．徐立中，王慧斌等，基于粗糙集理论的图像增强方法，仪器仪表学报，2000，
21(5):514-524
91．李男，邱天爽等，基于粗糙集的数据挖掘技术及其在临床医学诊断中的应
用，上海生物医学工程，第 23 卷第 2 期，pp3-7，2000 年.
92．胡静，曹先彬等，基于相容粗糙集的图形图像信息预检索，计算机辅助设
计与图形学学报，第 14 卷第 3 期，pp242-246，2000 年 3 月.
93．Z. M. Wojicik, A Natural Approach to Image Processing and Pattern Recognition:
Rotating Neighborhood Technique, Self-Adapting Threshold, Segmentation and
Shape Recognition, 1985, Pattern Recognition, 18(5): 299-326
94．唐正军，刘代志，改进多尺度 CANNY 算子在 SAR 图像边缘提取中的应用，
上海航天，2000，17(2): 7-10
95．刘曙光，刘明远，何钺，基于 Canny 准则的基数 B 样条小波边缘检测，信
号处理，2001，11(5): 418-423
96．杨烜，梁德群，杨万海，边缘检测中 Canny 算子、二次样条小波算子性能
分析，通信学报，1999，20(8): 47-51
97．解梅，马征，B 样条小波边缘检测算子的应用研究，电子学报，1999，27(1):
106-108
98．杨正远，郑建宏，小波在图象边缘检测中的应用，重庆邮电学院学报，1997，
9(1): 5-9
99．杨亚军，张红林，李言俊等，基于小波算子的图像边缘检测，弹箭与制导
学报，1998，4: 7-11
100．蔡靖，刘峰，丁润涛，模糊迭代边缘检测器，电子与信息学报，2001，23(2):
134-139
100．S.K. Pal, R.A. King, On edge detection of X-ray images using fuzzy sets, IEEE
Trans. On Patt. Anal.&Mach. Intel., 1983, 5(1): 69-77
101．Wang Hui, Multi-gray edge detection based on generalized fuzzy set, Journal of
Electronics, 2002, 19(4): 426-430
102．陈武凡，谢新朋，洪文松，广义模糊集合论及其在图像处理中的新应用，
生物医学工程学报，1999，18(1):66-73
103．熊兴华，李新涛，面向对象的遥感影像模糊增强，武汉大学学报·信息科
学版，2002，27(5): 516-521
104．S.K.Setarehdan, and J.J.Soraghan, Cardiac left ventricular volume changes
assessment by long axis echocardiographical image processing, IEE
Proceedings- Vision, Image and Signal Processing, 1998, 145(3): 203-212
105．S.K.Setarehdan, and J.J.Soraghan, Fuzzy Multiscale Edge Detection(FMED)
Applied to Autonetic LeftVebtricle Boundary Extraction, Image Processing and
100
参考文献
Its Applications, 1999. Seventh International Conference on (Conf. Publ. No.
465) , 1999, 2: 552-556.
１０６．S.K.Setarehdan, and J.J.Soraghan, AutomaticCardiacLVBoundaryDetection
and Tracking Using Hybrid Fuzzy Temporal and Fuzzy Multiscale Edge
Detection, IEEE Transactions on Biomedical Engineering, 1999, 46(11):
1364-1376.
107．C.Vertan, A.stoica, C.Fernandez-Maloigne, Perceptual Fuzzy Multiscale Color
Edge Detection, Fuzzy Systems, 2001, The 10th IEEE International Conference
on , 2001, 1: 19-22
１０８．边肇祺 编著，《模式识别》（第二版），清华大学出版社，2000，273-283
109．周峰，纹理分析中若干问题的研究：[博士学位论文]，2001，北京，北京
大学，2001: 1-10
110．吴高洪，章毓晋，林行刚，分割双纹理图像的最佳 Gabor 滤波器设计方法，
电子学报，2001，29(1): 48-50
111．郭立，朱俊株，陆大虎，基于 Gabor 小波变换的无监督纹理图像分割，微
机发展，2000，5: 51-54
112．吴高洪，章毓晋，林行刚，利用小波变换和特征加权进行纹理分割，中国
图象图形学报，2001，6(A)(4):333-337
113．胡召玲，郭达志，盛业华，基于小波分解的星载 SAR 图像纹理信息提取，
遥感学报，2001，5(6): 423-427
114．杨浩，裴继红，杨烜，基于小波框架分解和模糊软聚类的纹理图像分割方
法，西安工业学院学报，1999，19(2): 103-108
115．叶桦，章国宝，陈维南，基于小波变换的纹理图像分割，东南大学学报，
1999，29(1): 44-48
116．刘昉，赵荣椿，程敬之，提高超声图像纹理分析空间分辨率的研究，中国
生物医学工程学报，2001，20(6): 566-570
117．C.-T. Li, Multiresolution image segmentation integrating Gibbs sampler and
region merging algorithm, Signal Processing, 2003, 83(1): 67-78
118．S. Stan, G. Palubinskas, M. Datcu, Bayesian selection of the neighbourhood
order for Gauss-Markov texture models, Pattern Recognition Letters, 2002,
23(10): 1229-1238
119．郭英凯，杨杰，陆正刚，基于高斯-马尔可夫随机场和神经网络的无监督纹
理分割，红外与激光激光工程，2000，29(2): 5-8
120．杨绍国，尹忠科，罗炳伟，分形多尺度分离图像分割，模式识别与人工智
能，1998，11(3): 347-351
121．郭立，陆大虎，朱俊株，基于 Gabor 多通道滤波和 Hopfield 神经网络的纹
理图象分割，计算机工程与应用，2000，36(6): 39-41
122．郑肇葆，郑宏，潘励，纹理分类中遗传算法参数的选择，测绘学报，2000，
29(1): 35-39
101
参考文献
123．郑肇葆，郑宏，基于遗传算法的影像纹理分类，武汉测绘科技大学学报，
1998，23(4): 337-339
124．郑肇葆，郑宏，用遗传算法确定马尔柯夫随机场的最佳参数，武汉测绘科
技大学学报，2000，25(3): 221-225
125．马永军，方凯，方廷健，基于支持向量机和距离度量的纹理分类，中国图
象图形学报，2002，7(A)(11): 1151-1155
126．刘伟强，支持向量机载图像处理应用中若干问题研究，[硕士学位论文]，
南京，南京理工大学，2002
127．Michael S. Landy, Visual Perception of Texture, http://www.cns.nyu.edu/~msl/
texentry2.pdf
128．郦苏丹，张翠，王正志，基于马尔可夫随机场的 SAR 图象目标分割，中国
图象图形学报，2002，7(A)(8):794-799
129．J. E. Besag, Spatial interaction and the statistical analysis of lattice systems, J.
Roy. Statist. Soc. Ser. B B-36:192-235(1974).
130．J. W. Woods, Two-dimensional discrete Markovian fields, IEEE Transactions on
Information Theory, 1972, 18(2): 232-240
131．J. W. Woods, Correction to 'Two-Dimensional Discrete Markovian Fields', IEEE
Transactions on Information Theory, 1972, 18(4): 541-541
132．J. E. Besag, Efficiency of pseudo-likelihood estimates for simple Gaussian
fields, Biometrika, 1977, 64:616-618
133．S. Lakshmanan,H.Derin, Simultaneous parameter estimation and segmentation
of Gibbs random fields using simulated annealing, IEEE Trans. on Patt. Anal.
& Mach. Intel. , 1989, 11(8): 799-813
134．Mallat, S.G., A theory for multiresolution signal decomposition: the wavelet
representation. IEEE Trans. PatternAnal. Mach. Intell., 1989, 11(7): 674-693
135．Chang, T., Kuo, C.C.J., Texture analysis and classificationwith tree-structured
wavelet transform. IEEE Trans. on Image Process, 1993, 2 (4):429-447
136．Laine, A., Fan, J., Texture classifiation by wavelet packet signatures. IEEE
Trans. on PatternAnal. Mach. Intell., 1993, 15 (11):1186-1191
137．Unser, M., Texture classification and segmentation using wavelet frames. IEEE
Trans. Image Process., 1995, 4 (11), 1549-1560
138．Jing-Wein Wang, Chin-Hsing Chen , Wei-Ming Chien, Textureclassification
using non-separable two-dimensional wavelets，Pattern Recognition Letters，
1998, 19(13): 1225-1234
139．Laws K L., Rapid texture identification, SPIE, 1980, 238:376-380.
140．马作民，毛士艺，刘样林，SAR 图像非平稳性对图像模型和滤波降噪方法
的影响，北京航空航天大学学报，2001，27(6): 713-716
141．丁艺芳，基于小波变换和视觉系统的图像质量综合评价新算法，[博士学位
论文]，上海：上海交通大学，2001
102
参考文献
142．杜培军，RADARSAT 图象滤波的研究，中国矿业大学学报，2002，31(2):
132-137
143．李向吉，丁润涛，蔡靖，边缘检测器性能的客观定量评价，1999，21(5):
634-639
144．侯格贤，毕笃彦，吴成柯，图象分割质量评价方法研究，中国图象图形学
报，2000，5(A)(1):39-43
145．王爱民，沈兰荪，图像分割研究综述，测控技术，2000，19(5): 1-7
146．Zhang.Y J.,A survey on evaluation methods for image segmentation, Pattern
Recognition, 1996, 29(8): 1335-1346
147．Sahoo P K, Soltani S., Wong A.K.C., etc, Survey of thresholding techniques,
Comput Vision Graphics Image Process, 1988, 41(2): 233-260
148．Straters K., Gerbrands J.J., Three-dimensional image segmentation using a split,
merge and group approach, Pattern Recognition Letters, 1991, 24(12): 307-325
149．Abdou Ikram E., Pratt William K., Quantitative design and evaluationof
enhancement/thresholding edge detectors, Proc IEEE, 1979, 67(5): 753-763
150．Zhang Y. J., Gerbrands J.J., Objective and quantitative segmentation evaluation
and comparison, Signal Processing, 1994, 39(1-2): 43-54
151．A. Achim, A. Bezerianos, P. Tsakalides, Ultrasound image denoising via maxi-
mum a posteriori estimation of wavelet coefficients, Engineering in Medicine
and Biology Society, 2001. Proceedings of the 23rd Annual International Con-
ference of the IEEE, 2001, 3:2553 -2556
152．秦石成，秦兆冰等，心脏及血管功能的超声评价，郑州：郑州大学出版社，
2001，36-38
153．Hiroyuki Yoshida, Bilgin Keserci, David D. Casalino. Etc, Segmentation of liver
tumors in ultrasound images based on scale-space analysis of continuous
wavelet transform, Proc IEEE Ultrason Symp, 1998, 2:1713-1716
154．R. Ravhon, D. Adam, L. Zelmanovitch, Validation of Ultrasonic Image
Boundary RecognitioninAbdominalAorticAneurysm, IEEE Transactions on
medical imaging, 2001, 20(8): 751-763
155．Consolatina Liguori, Alfredo Paolillo,Antonio Pietrosanto, An Automatic Mea-
surement System for the Evaluation of Carotid Intima-Media Thickness,IEEE
Tans. on Instramentation and Measurement, 2001, 50(6): 1684-1691
156．Chung-Ming Wu, Yung-Chang Chen,Kai-Sheng Hsieh, Texture features for
classification of ultrasonic liver images, IEEE Trans onMedical Imaging, 1992,
11(2): 141-152
157．A.V. Oppenheim, R.W. Schafer, T.R. Buck, Discrete-TimeSignalProcessing
(Second Edtion)（离散时间信号处理，刘树堂，黄建国译），西安交通大学
出版社，2001，9，131-134