Snake模型在医学图像分割上的应用研究
|
摘要
医学图像处理是计算机领域的一个分支,是数字图像处理技术在生物医学工程中的重要应用。对医学图像进行目标轮廓提取,是临床诊断和科学研究的基础。活动轮廓线模型即Snake模型所特有的高度动态特性,使之非常适合于医学图像的分割和轮廓提取处理。本论文具体研究使用Snake模型解决医学图像目标轮廓提取所面临的关键技术问题。
把Snake模型应用于临床系统中,首先要解决的是初始轮廓线和参数难以确定的问题。本文抛弃使用工作人员手工勾勒初始轮廓的原始方法,提出结合基于标识分水岭算法的初始轮廓线获得方法,该方法能快速有效地得到趋近于实际边缘的初始轮廓线,为后面的模型迭代收敛打下基础。在设定参数上,根据活动轮廓模型中不同参数在不同时期的影响作用,预测估计非边缘点应调整到的目标位置和能量,求得下一平衡状态下参数数值从而达到自适应地调整参数的效果,使模型轮廓能更好地收敛于目标边缘。把目标的先验知识融入到活动轮廓模型中,是活动轮廓模型的发展趋势。本文结合医学图像本身的特点,使用曲线拟合的方法构造椭圆力场,使活动轮廓模型在形变过程中得以保持椭圆的形状,在分割椭圆类目标轮廓时能使模型在弱边缘处也得到很好的响应。
本论文通实验的手段证明了上述方法的有效性,并能快速简单地应用于临床系统之中。
As one research branch in the field of computer vision, medical image processing is an important application of computer graphics and digital image processing in the biomedical engineering. Extracting the object's contours from medical images is the foundation of diagnostic and sceince research. Active contour models (ACM) are very suitable to medical image segmentation and contour extracting due to its highly dynamic quality. The primary task of the thesis is to study the key points of applying ACM to solve problems of precessing medical images.
The first problem to be solved is how to confirm the initial contour and the parameters of the models. The thesis uses the method of initial contour selection of snake model based on watershed algorithm instead of the method of depicting the contours by manual. Result shows that the algorithm can quickly get the availabe contour that works well in the further process. For the parameters, we get the parameters by estimating the position and energy of non-edge points in the next balance state, so the parameters can be changed adaptively in order to get a better segmentation. Combining the prior knowledge of the medical images to the snake models is one of developing trends. This thesis analyse the characteristic of the medical images and improve the snake models with an extra elliptic force which is computed by elliptic curve fitting, which can maintain contours with the elliptic shapes during the converging process.
The experiments followed show that the methods above work well in the medical images and can be easily applied in clinic systems.
把Snake模型应用于临床系统中,首先要解决的是初始轮廓线和参数难以确定的问题。本文抛弃使用工作人员手工勾勒初始轮廓的原始方法,提出结合基于标识分水岭算法的初始轮廓线获得方法,该方法能快速有效地得到趋近于实际边缘的初始轮廓线,为后面的模型迭代收敛打下基础。在设定参数上,根据活动轮廓模型中不同参数在不同时期的影响作用,预测估计非边缘点应调整到的目标位置和能量,求得下一平衡状态下参数数值从而达到自适应地调整参数的效果,使模型轮廓能更好地收敛于目标边缘。把目标的先验知识融入到活动轮廓模型中,是活动轮廓模型的发展趋势。本文结合医学图像本身的特点,使用曲线拟合的方法构造椭圆力场,使活动轮廓模型在形变过程中得以保持椭圆的形状,在分割椭圆类目标轮廓时能使模型在弱边缘处也得到很好的响应。
本论文通实验的手段证明了上述方法的有效性,并能快速简单地应用于临床系统之中。
As one research branch in the field of computer vision, medical image processing is an important application of computer graphics and digital image processing in the biomedical engineering. Extracting the object's contours from medical images is the foundation of diagnostic and sceince research. Active contour models (ACM) are very suitable to medical image segmentation and contour extracting due to its highly dynamic quality. The primary task of the thesis is to study the key points of applying ACM to solve problems of precessing medical images.
The first problem to be solved is how to confirm the initial contour and the parameters of the models. The thesis uses the method of initial contour selection of snake model based on watershed algorithm instead of the method of depicting the contours by manual. Result shows that the algorithm can quickly get the availabe contour that works well in the further process. For the parameters, we get the parameters by estimating the position and energy of non-edge points in the next balance state, so the parameters can be changed adaptively in order to get a better segmentation. Combining the prior knowledge of the medical images to the snake models is one of developing trends. This thesis analyse the characteristic of the medical images and improve the snake models with an extra elliptic force which is computed by elliptic curve fitting, which can maintain contours with the elliptic shapes during the converging process.
The experiments followed show that the methods above work well in the medical images and can be easily applied in clinic systems.
引文
[1]田捷,包尚联,周明全.医学影像处理与分析[M].北京:电子工业出版社,2003.
[2]章毓晋.图像分割[M].北京:科学出版社,2001.
[3]J.C.Bezdek,L.O.Hall,and L.P.Clarke.Review of MR image segmentation techniques using pattern recognition[J].Med Phys,1993,20:1033-1048.
[4]L.P.Clarke,R.P.Velthuizen,M.A.Camacho,J.J.Heine,M.Vaidyanathan,et al.MRI segmentation:methods and applications[J].Magn.Res.Imag.1995,13:343-368.
[5]Liang,Z.Tissue classification and segmentation of MR imaging[J].IEEE Engr.Med.Biol.Mag.1993,12:81-85.
[6]A P Zijdenbos and B M Dawant.Brain segmentation and white matter lesion detection in MR images[J].Critical Reviews in Biomedical Engineering.199422:401-465.
[7]L P Clarke,R P Velthuizen,S Phuphanich,J D Schellenberg,J A Arrington,and M.Silbiger.MRI:stability of three supervised segmentation techniques[J].Mag.Res.Imag.1993,11:95-106.
[8]Bram Van Ginneken,Alejandro F Frangi,Joes J Staal,etal.Active Shape model segmentation with optimal features[J].IEEE Transactions on Medical Imaging,2002,21(8):924-933.
[9]Tim Mclnerney,Demetri Terzopoulos.Deformable models in medical image analysis[J].Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis,San Francisco,CA USA,21-22 June 1996,171-180.
[10]T.Behrens,K.Rohr,H.S.Stiehl.Robust segmentation of tubular structures in 3-D medical images by parametric object detection and tracking[J].IEEE Transactions on Systems.Man and Cybernetics,2003,33B(4):554-561.
[11]J.Liang,Mclnerney,D.Terzopolous.Interactive Medical Image Segmentation with United Snakes[J].Proceedings Lecture Notes in Computer Science:Medical Image Computing and Computer-Assisted Intervention MICC-AI,1999(1679):116-127.
铩颷12]Kirbas,C.Quek,F.K.H.Vessel Extraction Techniques and Algorithms:A Sur-Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
vey[J].Proceedings of the Third IEEE Symposium on Bioinformatics and Bioeng-Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
ineering.2003,238-245.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[13]Chen C W,Luo J,K J Parker,et al.A knowledge-based approach to volumetricQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
medical Image segmentation[J].IEEE International conference on ImageQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Processing,1994,3:493-497.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[14]P H Gregson.Automatic segmentation of the heart in 3D MR imagesQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[J].Canadian conference on electrical and computer engineering,NewQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
York;IEEE,1994,2:584-587.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[15]林瑶,田捷,张晓鹏.基于模糊连接度的FCM分割方法在医学图像分析中的应Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
用[J].中国体视学与图像分析,2001,6(2):103-108.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[16]Cheng Kuosheng,Lin Jzausheng,Mao Chiwu.The application of competitiveQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Hopfield neural network to medical image segrnentation[J].IEEE Trans.OnQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Medical Imageing.1996,15(4):560-567.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[17]M Kass,A P Witldn,D Terzopoulos.Snakes:active contour modals[J].Int JQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Computer Vis,1988;1(4):321-331.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[18]G Xu,E Segawa,and S Tsuji.Robust active contours with insensitiveQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
parameters[J].Pattern Recognition,1994,27(7):879-884.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[19]J O Lachaud and A Montanvert.Deformable meshes with automated topologyQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
changes for coarse-to-ne three-dimensional surface extraction[J].Medical ImageQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Analysis,1999.3(2):187-207.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[20]F Leitner and P Cinquin.Complex Topology 3D objects Segrnentation[J].In SPIEQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Conf.on Advances in Intelligent Robotics Systems,Nov.1991,Volume 1609.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[21]T McInerney and D Terzopoulos.Topologically adaptable snakes[J].ProceedingsQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
of the Fifth International Conference on Computer Vision,1995,840-845.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[22]Chakraborty,L H Staib,J S Duncan.Deformable Boundary Finding in MedicalQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Images by Integrating Gradient and Region Information[J].IEEE Transactions onQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Medical Imaging,1996,15(6):859-870.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[23]Remi Ronfard.Region based strategies for active contour models[J].InternationalQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Journal of Computer Vision,1994,13(2):229-251.
[24] J Ivins, J Porrill. Active Region Models For segmentiong Textures And Colours [J].Image and Vision Computing,1995,13(5):431-438.
[25]Wael-Abd Almageed, Christopher E.Smith. Mixture Models for Dynamic Statistical Pressure Snakes[J].ICPR(2),2002:721-724.
[26] S C Zhu and A Yuilie. Region competition:Unifying snakes,region growing,and Bayes/MDL for multiband image segmentation [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1996,18(9):884-900.
[27] N Paragios, and R Deriche. Geodesic active regions for motion estimation and tracking[J].In 7th IEEE International Conference on Computer Vision,Corfou, Greece,Sept. 1999:674-688.
[28] Toru Abe, Yuki Matsuzawa. A Region Extraction Method Using Multiple Active Contour Models[J].Computer Vision and Pattern Recognition,2000,1: 1064-1069.
[29] K Fukui. Contour Extraction Method based on separability of Image features [J].IEICE Trans.Inf.&syst, 1997,6:1406-1414.
[30] L D Cohen. On active contour modals and ballons[J].CVGIP: Image Understanding, 1991,53(2):211-218.
[31]L D Cohen, I Cohen. Finite-element method for active contour models and balloons for 2D and 3D images[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1993,15(11):1131-1147.
[32]Xu Chenyang, J L Prince. Snakes,shapes,and gradient vector flow[J].IEEE Trans Image Proc,1998;7(3):359~369.
[33]B Leroy, I Herliin, and L D Cohen. Multi-resolution algorithm for active contour models[J].In 12th Int. Conf.Analysis and Optimization of System,1996:58-65.
[34] A Yezzi, A Tsai, A Willsky. Fully Global Coupled Curve Evolution Equations for Image Segmentation[J].LIDS Technical Report.January,1999.
[35] Ji Lilian, Yan Hong. Attractable snakes based on the greedy algorithm for contour extraction[J] .Pattern Recognition,2002,3 5:791-806.
[36]Ji Lilian, Yan Hong. Loop-free snakes for highly irregular object shapes[J]. Pattern Recognition Letters,2002,23(5):579-591.
[37] A Amini, S Tehrani, T Weymouth.Using Dynamic Programming for Minimizing the Energy of Active Contours in the Presence of Hard Constraints[J].In
Proceedings of the 2nd international Conference of Computer Vision.Ieee
Computer Soc.Press,Tampa,Florida.1988:95-99.
[38]AA Amini,TE Weymouth,RC Jain.Using Dynamic Programming for Solving Variational Problems in Vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(9):855-867.
[39]DJ Williams,M Shah.A fast algorithm for active contours and curvature estimation[J].CVGIP:Image Understanding,1992,55(1):14-26.
[40]DJ Williams,S Mubarak.A fast algorithm for active contours and curvature estimation[J].CVGI:Image Understanding,1992,55(1):14-26.
[41]K M Lam,Yan Han.Fast greedy algorithm for active contours[J].Electronic Letters,1994,30(1):21-22.
[42]S Menet,P Saint-Marc,G Medioni.B-Snakes:Implementation and application to stereo[J].In Proceedings of Third International Conference on Computer Vision,1990:720-726.
[43]Wang Yue.Earn Khwang Teoh,Dinggang Shen.A b-snake model using statistical and geometric information[J].Image and Vision Computing.2000,22:269-280.
[44]G Storvik.A Bayesian approach to dynamic contours through stochastic samplingand simulated annealing[J].IEEE Trans.on Pattern Analysis and Machine Intelligence.1994,16(10):976-986.
[45]L Ballerini.Genetic Snakes for Medical Images Segmentation[J].In Mathmatical Modeling and Estimation Techniques in Computer Vision,Preteux,Davison and Dougherty ed.,Proc.SPIE.1998,3457:284-295.
[46]Tsai C-T,Sun Y-N,Chung P-C.Minimising the energy of active contour model using a Hopfield network[J].1993,140(6):297-303.
[47]李天庆,张毅,刘志,胡东成等.Snake模型综述[J].计算机工程,2005;31(9):1-3
[48]李丽勤,高焕文,周兴祥等.Snake模型初始轮廓选取的研究[J].计算机工程与应用,2004;40(11):43-45.
[49]F Meyer,S beucher.Morphology segrnentation[J].J Visual Comm and Image Representation,1900;1(1),21-26.
铩颷50]王元全,汤敏,王平安等.基于先验知识改进Snake模型的脸部特征分割[J].计算Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
机辅助设计与图形学学报.2004;16(5):687-690.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[51]刘书桂,李蓬,那永林.基于最小二乘原理的平面任意位置椭圆的评价[J].计Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
量学报,2002,23(4):10.
[2]章毓晋.图像分割[M].北京:科学出版社,2001.
[3]J.C.Bezdek,L.O.Hall,and L.P.Clarke.Review of MR image segmentation techniques using pattern recognition[J].Med Phys,1993,20:1033-1048.
[4]L.P.Clarke,R.P.Velthuizen,M.A.Camacho,J.J.Heine,M.Vaidyanathan,et al.MRI segmentation:methods and applications[J].Magn.Res.Imag.1995,13:343-368.
[5]Liang,Z.Tissue classification and segmentation of MR imaging[J].IEEE Engr.Med.Biol.Mag.1993,12:81-85.
[6]A P Zijdenbos and B M Dawant.Brain segmentation and white matter lesion detection in MR images[J].Critical Reviews in Biomedical Engineering.199422:401-465.
[7]L P Clarke,R P Velthuizen,S Phuphanich,J D Schellenberg,J A Arrington,and M.Silbiger.MRI:stability of three supervised segmentation techniques[J].Mag.Res.Imag.1993,11:95-106.
[8]Bram Van Ginneken,Alejandro F Frangi,Joes J Staal,etal.Active Shape model segmentation with optimal features[J].IEEE Transactions on Medical Imaging,2002,21(8):924-933.
[9]Tim Mclnerney,Demetri Terzopoulos.Deformable models in medical image analysis[J].Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis,San Francisco,CA USA,21-22 June 1996,171-180.
[10]T.Behrens,K.Rohr,H.S.Stiehl.Robust segmentation of tubular structures in 3-D medical images by parametric object detection and tracking[J].IEEE Transactions on Systems.Man and Cybernetics,2003,33B(4):554-561.
[11]J.Liang,Mclnerney,D.Terzopolous.Interactive Medical Image Segmentation with United Snakes[J].Proceedings Lecture Notes in Computer Science:Medical Image Computing and Computer-Assisted Intervention MICC-AI,1999(1679):116-127.
铩颷12]Kirbas,C.Quek,F.K.H.Vessel Extraction Techniques and Algorithms:A Sur-Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
vey[J].Proceedings of the Third IEEE Symposium on Bioinformatics and Bioeng-Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
ineering.2003,238-245.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[13]Chen C W,Luo J,K J Parker,et al.A knowledge-based approach to volumetricQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
medical Image segmentation[J].IEEE International conference on ImageQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Processing,1994,3:493-497.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[14]P H Gregson.Automatic segmentation of the heart in 3D MR imagesQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[J].Canadian conference on electrical and computer engineering,NewQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
York;IEEE,1994,2:584-587.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[15]林瑶,田捷,张晓鹏.基于模糊连接度的FCM分割方法在医学图像分析中的应Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
用[J].中国体视学与图像分析,2001,6(2):103-108.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[16]Cheng Kuosheng,Lin Jzausheng,Mao Chiwu.The application of competitiveQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Hopfield neural network to medical image segrnentation[J].IEEE Trans.OnQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Medical Imageing.1996,15(4):560-567.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[17]M Kass,A P Witldn,D Terzopoulos.Snakes:active contour modals[J].Int JQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Computer Vis,1988;1(4):321-331.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[18]G Xu,E Segawa,and S Tsuji.Robust active contours with insensitiveQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
parameters[J].Pattern Recognition,1994,27(7):879-884.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[19]J O Lachaud and A Montanvert.Deformable meshes with automated topologyQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
changes for coarse-to-ne three-dimensional surface extraction[J].Medical ImageQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Analysis,1999.3(2):187-207.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[20]F Leitner and P Cinquin.Complex Topology 3D objects Segrnentation[J].In SPIEQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Conf.on Advances in Intelligent Robotics Systems,Nov.1991,Volume 1609.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[21]T McInerney and D Terzopoulos.Topologically adaptable snakes[J].ProceedingsQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
of the Fifth International Conference on Computer Vision,1995,840-845.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[22]Chakraborty,L H Staib,J S Duncan.Deformable Boundary Finding in MedicalQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Images by Integrating Gradient and Region Information[J].IEEE Transactions onQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Medical Imaging,1996,15(6):859-870.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[23]Remi Ronfard.Region based strategies for active contour models[J].InternationalQuery =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
Journal of Computer Vision,1994,13(2):229-251.
[24] J Ivins, J Porrill. Active Region Models For segmentiong Textures And Colours [J].Image and Vision Computing,1995,13(5):431-438.
[25]Wael-Abd Almageed, Christopher E.Smith. Mixture Models for Dynamic Statistical Pressure Snakes[J].ICPR(2),2002:721-724.
[26] S C Zhu and A Yuilie. Region competition:Unifying snakes,region growing,and Bayes/MDL for multiband image segmentation [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 1996,18(9):884-900.
[27] N Paragios, and R Deriche. Geodesic active regions for motion estimation and tracking[J].In 7th IEEE International Conference on Computer Vision,Corfou, Greece,Sept. 1999:674-688.
[28] Toru Abe, Yuki Matsuzawa. A Region Extraction Method Using Multiple Active Contour Models[J].Computer Vision and Pattern Recognition,2000,1: 1064-1069.
[29] K Fukui. Contour Extraction Method based on separability of Image features [J].IEICE Trans.Inf.&syst, 1997,6:1406-1414.
[30] L D Cohen. On active contour modals and ballons[J].CVGIP: Image Understanding, 1991,53(2):211-218.
[31]L D Cohen, I Cohen. Finite-element method for active contour models and balloons for 2D and 3D images[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,1993,15(11):1131-1147.
[32]Xu Chenyang, J L Prince. Snakes,shapes,and gradient vector flow[J].IEEE Trans Image Proc,1998;7(3):359~369.
[33]B Leroy, I Herliin, and L D Cohen. Multi-resolution algorithm for active contour models[J].In 12th Int. Conf.Analysis and Optimization of System,1996:58-65.
[34] A Yezzi, A Tsai, A Willsky. Fully Global Coupled Curve Evolution Equations for Image Segmentation[J].LIDS Technical Report.January,1999.
[35] Ji Lilian, Yan Hong. Attractable snakes based on the greedy algorithm for contour extraction[J] .Pattern Recognition,2002,3 5:791-806.
[36]Ji Lilian, Yan Hong. Loop-free snakes for highly irregular object shapes[J]. Pattern Recognition Letters,2002,23(5):579-591.
[37] A Amini, S Tehrani, T Weymouth.Using Dynamic Programming for Minimizing the Energy of Active Contours in the Presence of Hard Constraints[J].In
Proceedings of the 2nd international Conference of Computer Vision.Ieee
Computer Soc.Press,Tampa,Florida.1988:95-99.
[38]AA Amini,TE Weymouth,RC Jain.Using Dynamic Programming for Solving Variational Problems in Vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(9):855-867.
[39]DJ Williams,M Shah.A fast algorithm for active contours and curvature estimation[J].CVGIP:Image Understanding,1992,55(1):14-26.
[40]DJ Williams,S Mubarak.A fast algorithm for active contours and curvature estimation[J].CVGI:Image Understanding,1992,55(1):14-26.
[41]K M Lam,Yan Han.Fast greedy algorithm for active contours[J].Electronic Letters,1994,30(1):21-22.
[42]S Menet,P Saint-Marc,G Medioni.B-Snakes:Implementation and application to stereo[J].In Proceedings of Third International Conference on Computer Vision,1990:720-726.
[43]Wang Yue.Earn Khwang Teoh,Dinggang Shen.A b-snake model using statistical and geometric information[J].Image and Vision Computing.2000,22:269-280.
[44]G Storvik.A Bayesian approach to dynamic contours through stochastic samplingand simulated annealing[J].IEEE Trans.on Pattern Analysis and Machine Intelligence.1994,16(10):976-986.
[45]L Ballerini.Genetic Snakes for Medical Images Segmentation[J].In Mathmatical Modeling and Estimation Techniques in Computer Vision,Preteux,Davison and Dougherty ed.,Proc.SPIE.1998,3457:284-295.
[46]Tsai C-T,Sun Y-N,Chung P-C.Minimising the energy of active contour model using a Hopfield network[J].1993,140(6):297-303.
[47]李天庆,张毅,刘志,胡东成等.Snake模型综述[J].计算机工程,2005;31(9):1-3
[48]李丽勤,高焕文,周兴祥等.Snake模型初始轮廓选取的研究[J].计算机工程与应用,2004;40(11):43-45.
[49]F Meyer,S beucher.Morphology segrnentation[J].J Visual Comm and Image Representation,1900;1(1),21-26.
铩颷50]王元全,汤敏,王平安等.基于先验知识改进Snake模型的脸部特征分割[J].计算Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
机辅助设计与图形学学报.2004;16(5):687-690.Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
[51]刘书桂,李蓬,那永林.基于最小二乘原理的平面任意位置椭圆的评价[J].计Query =
CADORecordset Error
Code = 80040e31
Code meaning = IDispatch error #3121
Source = Microsoft OLE DB Provider for SQL Server
Description = 超时已过期
量学报,2002,23(4):10.