摘要
图像分割作为图像处理的基础环节,一直是图像工程领域中的热点和难点问题。几十年来,研究者们不断探索新的图像分割方法,以使求解的问题更逼近于实际应用。水平集方法作为一种新的基于偏微分方程的图像处理方法,具有自由拓扑变换以及易集成多种特征或多种方法的优点,最近受到图像分割领域众多学者的关注。但是,随着图像处理技术应用范围的日益广泛和用户需求的不断提高,图像分割所面临的问题也日趋复杂化。
在此背景下,本文针对复杂场景(主要针对灰度不均匀、光谱异质、目标类型多且拓扑关系复杂的场景)中水平集图像分割方法存在的分割精度不高、局部极小解及分割速度慢等主要问题,开展了基于水平集方法的图像分割关键技术研究。论文的主要工作包括:
1、为解决灰度不均匀现象对图像分割的干扰问题,开展变分单水平集图像分割方法研究。基于灰度不均匀图像在邻域范围内特征保持相对稳定的特征分析,提出一种新的邻域偏移场估计方法;并在此基础上构建变分单水平集分割模型,以缓解各种程度的灰度不均匀及伴随的弱边界和噪声等现象对图像分割产生的不利影响。此外,开展下行随机优化方法的研究以解决变分水平集模型求解中通常存在的局部极小现象,实现近似全局最优的图像划分。
2、为解决多水平集图像分割中参数法概率密度估计的不足及混分现象,开展非参多水平集图像分割方法研究。首先采用Parzen窗非参数密度估计实现复杂场景下样本分析建模,并以此构建基本的非参多水平集分割模型;再利用Gabor小波的纹理分析能力改善模型的分类性能;此外,通过邻域像素的相位特征分析提出一种邻域类相似度函数,并基于此函数构造类别约束项,以缓解遥感图像中光谱异质、噪声等干扰引起的类别错分问题。
3、为克服传统的基于像素图像分割方法易受噪音或冗余细节影响这一不足,开展条件随机多水平集图像分割方法研究。条件随机场理论利用概率图模型表达空间邻域关系,并具有概率推理的优势。基于条件随机场理论在数据分类中的优势,本论文将其同水平集方法结合。首先,设计一种竞争多类划分策略,并在此基础上提出新的多类划分条件随机场概率模型;再通过离散变量的连续化映射,将上述竞争条件随机场概率模型融合到多水平集图像分割方法中,以增强水平集分割模型对噪声或细节的抗干扰能力,提高分类精度。
4、为解决水平集模型求解效率低的问题,开展快速水平集图像分割方法研究。通过对水平集能量变化与样本分布状态的相关性分析,本文提出一种新的加速方法,用目标样本密度的变化引导曲线快速演化,以达到加快单水平集、多水平集分割模型求解速度的目的。
Image segmentation, as an important aspect in image processing, has been a hot but a formidable problem in an image project. For decades, researchers have been constantly seeking and exploring new ways to image partition, in order to the addressed problems more close to practical applications. Level set methods, as a type of novel image processing technology based on partial differential equation, have the advantages of free topology changes and easy integration of multi-cues(color, texture, shape, etc.), the kind of methods has been attracting much attentions from scholars in image segmentation field in recent years. However, problems facing to people in image segmentation are becoming increasingly complex with more extensive applications of image processing technologies and increasing users’demands.
In the context, focusing on critical problems in image segmentation to be addressed including: poor accuracy of image segmentation especially in complex scene, local minima problems commonly existing in level set methods, slow speed of segmentation, in a complex scene(mainly as intensity inhomogeneity, spectral hetegeneity, multiple objects with complex topology relation), the thesis presents some subjects to be studied. The subjects are mainly as follows:
1. To solve the problem caused by intensity inhomogeneity usually existing in images, this thesis develops a variational level set method for image segmentation. Based on the fact that features of intensity inhomogeneity keep relatively stable in a neighboring range of a given image, a neighbor offset field estimation method is developed. On the basis, a variational level set model for image segmentation has been constructed in order to alleviate disturbances from intensity inhomogenity, the coupled weak boundary, and noises. In addition, the thesis proposes a simple and effective downlink random optimization method so as to search an approximately global optimal solution. The purpose is to solve problems of local minimum occurring to traditional level set methods.
2. To solve the problem of misclassification existing in multiple level set segmentation, this thesis studies on a multiple level set method based on non-parameterization density estimation. Specifically, Parzen Window density estimation is firstly introduced to develop samples analysis and density modelling in complex scenes in order to build a basic non-parameterization multiple level set segmentation framework. Then, a Gabor filter bank is used in texture analysis to improve the classification performance. In addition, a neighbor similarity function is suggested and then a new class constraint energy item is constructed in order to further alleviate misclassification caused by spectral heterogeneity or noises, etc..
3. To overcome the shortages of traditional pixel-based segmentation methods, a study on multiple level set method driven by Conditional Random Fields is developed. Conditional Random Fields theory has unique advantages of spatial context analysis using probability graph model and probability inference in image segmentation. Based on the advantages, the thesis combines the theory with a multiple level set method. Specifically, a strategy used to multi-class image partition based on competition between classes is proposed to create a probability model. Secondly, the proposed probability model is combined into level set framework through a mapping operation of discrete variables into continuous ones, in order to enhance the ability of resistance to noises, details interferences and to improve accuracy of image segmentation.
4. In order to solve the problem of low-efficiency in solving the level set methods, a fast level set method for image segmentation is studies. Specifically, this thesis presents a novel fasten method of level set model for image segmentation through a correlation analysis between the amount of energy changes of each level set function and sample density in order to fasten curve evolution driven by a change of samples density either for two-phase level set, multi-phase level set segmentation model .
引文
[1]章毓晋.图像分割[M].北京:科学出版社. 2001: 1-26页
[2] M.Sonka, V.Hlavac, R.Boyle. Image Processing, Analysis, and Machine Vision[M]. Beijing: Posts and Telecom Press. 2003: 123-190P
[3]章毓晋.图像工程II.图像分析[M].北京:清华大学出版社出版. 2005: 73-90页
[4]王大凯,侯榆青,彭进业.图像处理的偏微分方程方法[M].北京:科学出版社. 2008: 80-108页
[5]林亚忠.基于Gibbs随机场模型的医学图像分割新算法研究[D].第一军医大学. 2004: 1-5页
[6]林瑶,田捷.医学图像分割方法综述[J].模式识别与人工智能. 2002,15(2): 192-204页
[7]单勇.复杂条件下视频运动目标检测和跟踪[D].国防科技大学. 2006: 1-7页
[8]常发亮.彩色图像分割与复杂场景下视觉目标跟踪方法研究[D].山东大学. 2005: 1-12页
[9] A.S.Laliberte, A.Rango, Texture and Scale in Object-Based Analysis of Subdecimeter Resolution Unmanned Aerial Vehicle (UAV) Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing. 2009, 47(3):761-770 P
[10] B.Thomas, L.Stefan, J.Geoffrey. Object-Based Image Analysis: Spatial Concepts for Knowledge-Driven Remote Sensing Applications[M]. Springer Publishing Company, Incorporated, 2008: 1-100 P
[11]杨新,李俊,杜啸晓.图像偏微分方程的原理与应用[M].上海:上海交通大学出版社,2003: 13-57页
[12]钱芸,张英杰.水平集的图像分割方法综述[J].中国图象图形学报. 2008,(01):786-793页
[13] S.Osher, J.A Sethian. Fronts propagation with curvature-dependent speed:algorithms based on Hamilton-Jacobi formulations [J]. Journal of Computation physics. 1988,79:12-49 P
[14] D.Adalsteinsson, J.A. Sethian. A fast level set method for propagating interfaces[J]. J. C. Ph.. 1995, 118(2):269–277 P
[15] J.Sethian. Level Set Methods and Fast Marching Methods[M]. Cambridge University Press. 1999:15-165 P
[16] D.Mumford, J.Shah. Optimal approximation by piece-wise smooth functions and associated variational problems[J]. Communications on Pure and Applied Mathematics. 1989,42:577-685 P
[17] T.Chan, L. Vese. Active contours without edges. IEEE Transaction Image Processing. 2001, 10(2):266-277 P
[18] Y.N.Law, H.K.Lee, A.M.Yip. A multi-resolution stochastic level set method for Mumford-Shah image segmentation[J]. IEEE Transactions On Image Processing. 2008, 17(12): 2289-2300 P
[19] L.A.Vese, T.F.Chan. A multiphase level set framework for image segmentation using the Mumford-Shah model[J]. International Journal of Computer Vision. 2002, 50:271-293 P
[20]潘振宽,李华,魏伟波等.三维图像多相分割的变分水平集方法[J].计算机学报. 2009,32(12):2464-2474页
[21] M.Burger, S.J.Osher, , A survey on level set methods for inverse problems and optimal design[J]. European Journal of Applied Mathematics. 2005, 16(2): 263-301 P
[22] A.R.Mansouri, A.Mitiche, C.Va′zquez. Multiregion competition: A level set extension of region competition to multiple region image partitioning[J]. Computer Vision and Image Understanding. 2006, 101:137-150 P
[23] H.K.Zhao, T.Chan, B.Merriman, S.Osher. A variational level set approach to multiphase motion[J]. J. Comput. Phys.1996,127: 179-195 P
[24] C.Samson, L.Blanc-Feraud, G.Aubert, et al.. A level set model for image classification[J]. IJCV 2000, 40(3): 187-197 P
[25] T.Brox, D.Cremers. On the Statistical Interpretation of the PiecewiseSmooth Mumford-Shah Functional[J]. Springer, LNCS, 2007, 4485:203-213P
[26] C.M. Li, C.Kao, J.Gore et al.. Minimization of Region-Scalable Fitting Energy for Image Segmentation[J]. IEEE Trans Image Processing. 2008, 17(10):1940-1949 P
[27] V.Caselles, T.Catte, T.Coll, et al.. A geometricmodel for active contours in image p rocessing[ J ]. Numeric Math, 1993, 66(1): 1-31 P
[28] R.Malladi, J.A.Sethian, B.C.Vemuri. A topology independent shape modeling scheme[A]. In: Proceedings of SPIE Conference, Geometric Methods Computer Vision II. 1993,2031: 246-258 P
[29] R.Malladi, J.A.Sethian, B.C.Vemuri. Shape modeling with front propagation: a Level Set approach[J]. IEEE Transaction On Pattern Analysis and Machine Intelligence. 1995, 17(2):158-175 P
[30] V.Caselles, R.Kimmel, G.Sapiro. Geodesic active contours[J]. International Journal of Computer Vision. 1997,22(1):61-79 P
[31] G.Kuhne, J.Weickert, B.Markus, et al.. Fast Implicit Active Contour Models[M]. Lecture Notes in Computer Science. 2002, 2449: 133-140.
[32] A.Yezzi, S.Kichenassamy, A.Kumar et al.. A geometric snake model for segmentation of medical imagery[J]. IEEE Transaction on Medical Imaging. 1997,16(2):199-209 P
[33]潘青,徐国良.曲面变形的水平集方法[J].计算机学报. 2009,(02): 213-220页
[34]段侪杰,马竟锋,张艺宝等.能量传导模型及在医学图像分割中的应用(英文)[J].软件学报. 2009,20(5):1106-1115页
[35]于力.虹膜图像的特征分析研究[D].哈尔滨工业大学. 2006: 71-84页
[36]王震.主动轮廓模型在人脸人耳检测方面的应用[D].哈尔滨工业大学. 2006:20-45页
[37]王元全,贾云得.一种心脏核磁共振图像左室壁内、外膜分割方法[J].软件学报. 2009, (05):1176-1184页
[38]万成凯,袁保宗,苗振江.一种基于活动轮廓和Gauss背景模型的固定摄像机运动目标分割算法[J].中国科学(F辑:信息科学). 2009, 39(4):391-396页
[39]祝轩.基于偏微分方程的图像去噪、修复及放大研究[D].西北大学, 2008:49-72页
[40]原达,张彩明,李晋江,刘晓华.基于Mumford-Shah模型的高精度MR图像轮廓提取算法[J].计算机学报. 2009, 32(02): 43-48页
[41]刘国才,王耀南.基于知识的多层Mumford-Shah向量值图像分割模型[J].自动化学报. 2009, 35 (4): 356-363页
[42]沈美丽.尿沉渣有形成分自动分类系统研究[D].长春理工大学. 2006:45-63页
[43] H.Mao, H.Liu, P.Shi. Neighbor-constrained active contours without edges. CVPR, 2008: 1-7.
[44]刘军伟.基于水平集的图像分割方法研究及其在医学图像中的应用[D].中国科学技术大学. 2009:81-90页
[45]郝家胜.基于几何流的医学图像分割方法及其应用研究[D].哈尔滨工业大学. 2008:37-47页
[46]朱国普.基于活动轮廓模型的图像分割[D].哈尔滨工业大学. 2007:79-83页
[47]金东晖.基于水平集的股骨头核磁共振图片分割方法研究[D].哈尔滨工业大学. 2007:55-70页
[48]俞璐.灰度图像分割技术研究[D].东南大学. 2007: 11-38页
[49]陈允杰.脑核磁共振图像与虚拟人脑图像分割技术研究[D].南京理工大学. 2008:57-85页
[50]陈强.图像分割若干理论方法及应用研究[D].南京理工大学. 2007: 29-80页
[51]杨耘,马洪超,林颖等.多水平集演化的高分辨率遥感图像分割[J].武汉大学学报(信息科学版). 2008, 33(06): 588-591页
[52]曹宗杰,闵锐,庞伶俐,皮亦鸣.基于统计模型的变分水平集SAR图像分割方法[J].电子与信息学报. 2008,(12): 2862-2866页
[53]郑罡,王惠南,李远禄.基于Chan-Vese模型的树形结构多相水平集图像分割算法[J].电子学报. 2006, 34(08): 1508-1512页
[54]周昌雄.基于活动轮廓模型的图像分割方法研究[D].南京航空航天大学. 2005: 55-70页
[55] G.Cao, Z.Mao, X.Yang. Optical aerial image partitioning using level sets based on modified Chan-Vese model[J]. Patter Recognition Letters. 2008, 29:457-464 P
[56]芦碧波.图像处理中的若干非线性扩散模型及其数值计算[D].吉林大学. 2008: 23-79页
[57]曾鹏鑫.动态场景下多运动目标检测及跟踪方法研究[D].东北大学. 2005:32-50页
[58]何宁.基于活动轮廓模型的图像分割研究[D].首都师范大学. 2009:21-67页
[59]李国友.基于广义模糊集及主动轮廓线模型的图像分割方法研究[D].燕山大学. 2006: 36-60页
[60]贾迪野.基于偏微分方程的图像平滑与分割研究[D].哈尔滨工程大学. 2005:20-39页
[61] N.Paragios, R.Deriche, Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000:266-280 P
[62] S.C Zhu, A.L.Yuille. Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation[J]. IEEE Trans. on PAMI . 1996, 18( 9): 884-900 P
[63] A.Tsai, A.Yezzi, A.S.Willsky, Curve evolution implementation of the Mumford–Shah functional for image segmentation, denoising, interpolation, and magnification[J]. IEEE Transaction Image Processing. 2001,10(8):1169–1186 P
[64]何传江,李梦,詹毅.用于图像分割的自适应距离保持水平集演化[J].软件学报. 2008, 19(12):3161-3169页
[65]刘复昌.核磁共振图像左心室轮廓的自动及交互分割方法研究[D].南京理工大学. 2009:21-58页
[66]沈毅,王艳,郝家胜.一种增量式变分水平集快速医学图像分割方法[P].中国专利:CN101315699, 2008-12-03页
[67]税午阳,周明全,耿国华.磁共振颅脑图像的脑组织自动获取方法[J].软件学报. 2009, 20(5):1139-1145页
[68]王斌,高新波.基于水平集接力的图像自动分割方法[J].软件学报.2009,20(5):1185-1194页
[69]曹宗杰,闵锐,庞伶俐,皮亦鸣.基于统计模型的变分水平集SAR图像分割方法[J].电子与信息学报. 2008, 36(12): 2862-2866页
[70]陈志彬;邱天爽.一种基于FCM和Level Set的MRI医学图像分割方法[J].电子学报. 2008, 36(09): 1733-1736页
[71]高齐新,杨金柱,赵大哲等.一种基于Canny算子的level-set肺部血管分割算法[J].系统仿真学报. 2008,20(20): 5534-5537页
[72]梅雪,夏良正,李久贤.一种基于变分水平集的红外图像分割算法[J].电子与信息学报. 2008, 30(07):1700-1702页
[73]谢振平,王士同.融合模糊聚类的Mumford-Shah模型[J].电子学报. 2008, 36(1):128-136页
[74] M.Leventon. Statistical models in medical image analysis[D]. Massachusets Institute of Technology. 2000: 105-115 P
[75] D.Cremers. Nonlinear Dynamical Shape Priors for Level Set Segmentation[J]. Journal of Scientific Computing. 2008, 35(2):132-143 P
[76] H.Heike, E. Jan, P. Xavier et al.. Level Set Segmentation Using a Point-Based Statistical Shape Model Relying on Correspondence Probabilities[C]. In Proc. of MICCAI Workshop Probabilistic Model for Medical Image Analysis (PMMIA'09), 2009: 1-10 P
[77] S.Q.Chen, R.J.Richard. Level Set Segmentation with Both Shape and Intensity Priors[C]. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2009:1-8 P
[78]董建园,郝重阳.基于统计先验形状的水平集图像分割综述[J].计算机科学. 2010,37(1):6-9页
[79] J.Liu, C.Smith, H.Chebrolu. A Local Probabilistic Prior-Based Active Contour Model for Brain MR Image Segmentation. ACCV (1) 2007: 956-964.
[80] N.Xu, Z.Yang, L.Zhang. A New Deformable Model Using Level Sets for Shape Segmentaltion. Journal of Electronics(China). 2009, 26(3):353-358 P
[81] E.Hodneland, X.C.Tai, Hans-Hermann Gerdes: Four-Color Theorem and Level Set Methods for Watershed Segmentation[J]. International Journal of Computer Vision. 2009, 82(3): 264-283 P
[82] S.Tse, L.Bradbury, W.L. Wan et al..A Combined Watershed and Level Set Method for Segmentation of Brightfield Cell Images[J]. Proceedings of SPIE Symposium on Medical Imaging. 2009, 7258:1-10 P
[83] J.S.Hao, Y.Shen, Q.Wang. Segmentation for MR A Image: An Improved Level-Set Approach[J]. IEEE Transactions on Instrumentation and Measurement .2007, 56(4):135-140 P
[84] S.Wang, S.G.Fu, Shenggao, L.C.Jiao et al.. An improved contour detection method based on level set and watershed transform[C]. MIPPR: Automatic Target Recognition and Image Analysis. 2009, 7495:1-6 P
[85] J.Liu, X.Yuan. Automated Breast Cancer Diagnosis using Level-set Statistics and Support Vector Machines[C]. the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2008:3044-3047 P
[86] Z.Zhang, S.Zhang, C.X.Zhang et al.. SVM for density estimation and application to medical image segmentation[J]. J Zhejiang Univ Sci B. 2006 , 7(5):365-72 P
[87]胡正平,张晔.基于SVM能量模型的改进主动轮廓图像分割算法研究.电子学报[J]. 2006, 34 (05): 930-933页
[88] S.Li, T.Fevens, A.Krzyak et al.. Automatic clinical image segmentation using pathological modelling. PCA and SVM[C]. In: International conference on machine learning and data mining in pattern recognition. Springer Verlag LNAI 2005, 3587:314-324 P
[89] E.Bae, X.C.Tai. Graph Cut Optimization for the Piecewise Constant Level Set Method Applied to Multiphase Image Segmentation[C]. SSVM 2009: 1-13 P
[90] Xiang Zeng, Wei Chen, Qunsheng Peng. A Novel Unified Variational Image Editing Model[J]. In Journal of Computer Science and Technology (JCST). 2006, 21(2):3456-3460 P
[91] P.G. Tiril, X. Tai.3D Multiphase Piecewise Constant Level Set Method Based on Graph Cut Minimization.Numerical Mathematics A Journal Of Chinese Universities English Series.2009, 2(4):403-420 P
[92] P.M.Jodoin, V.Saligrama, J. Konrad. Statistical Background Subtraction Using Spatial Cues[J]. IEEE Trans. Circuits Syst. Video Techn.2007, 17(12): 1758-1763 P
[93] D.Cobzas, M.Schmidt. Increased discrimination in level set methods with embedded conditional random fields[J]. IEEE Conference on Computer Vision and Pattern Recognition. 2009, 18(3): 328-335 P
[94] G.Tsechpenakis, D.N.Metaxas. CoCRF deformable model: a geometric model driven by collaborative conditional random fields[J]. IEEE Transactions on Image Processing, 2009, 18(10):2316-2329 P
[95] C. Li, C. Xu, C. Gui et al.. Level set evolution without re-initiation: a new variational formuation [C]. IEEE Conference on Computer Vision and Pattern Recognition. 2005, 1: 430-436 P
[96] J.Chung, L.Vese. Energy minimization based segmentation and denoising using a multilayer level set approach[C]. in Energy Minimization Methods in Computer Vision and Pattern Recognition. Springer, 2005, 3757: 439-455P
[97] J.Chung, L.Vese. Image segmentation using a multilayer level-set approach[J]. Computing and Visualization in Science.Springer, 2009, 12(6): 267-285 P
[98] A.R.Mansouri, A.Mitiche, C.Va′zquez. Image partioning by level set multiregion competition[C]. ICIP 2004, 2721-2724 P
[99]郭振波.基于变分水平集方法的多相图像分割研究[D].中国海洋大学. 2008: 47-73页
[100] C.Va′zquez, A.R.Mansouri, A. Mitiche. Approximation of images by basis functions for multiple region segmentation with level sets. ICIP 2004:549-552 P
[101] T.Brox, J.Weickert. Level Set Based Image Segmentation with Multiple Regions[J]. In Pattern Recognition, Springer LNCS 3175,2004, 8: 415-423 P
[102] J.E.Ball, L.M. Bruce. Level Set Segmentation of Remotely Sensed Hyper-spectral Images[C]. IGARSS '05,2005, 8: 5638- 5642 P
[103] C.Li, R.Huang, Z.Ding, C.Gatenby et al.. A variational level set approach to segmentation and bias correction of images with intensity inhomogeneity[C]. MICCAI. 2008:1083-1091 P
[104] M.Jeon, M.Alexander, N.Pizzi, et al.. Unsupervised hierarchical multi-scale image segmentation Level Set. wavelet and additive splitting operator[C]. Proceedings of the North American Fuzzy Information Processing Society, Canada, 2004, 664-668 P
[105] I.B.Ayed, A.Mitiche, Z.Belhadj. Multiregion Level Set Partitioning of Synthetic Aperture Radar Images[J]. IEEE Trans. Pattern Analysis and Machine Intelligence. 2005, 27(5): 793-800 P
[106] O.Besbesy, Z.Belhadj, N.Boujema. A Variational Framework for Adaptive Satellite Images Segmentation[C].Springer Verlag: Lecture Notes in Computer Science, 2007, 4485:675-686 P
[107] D.Larlus , F.Jurie. Combining appearance models and Markov random fields for category level object segmentation[C]. IEEE conference on Computervision and pattern recognition, 2008: 1-7 P
[108] Y.Guo, C.Rao, S.Samarasekera, et al.. Matching vehicles under large pose transformations using approximate 3D models and piecewise MRF model[C]. IEEE conference on Computervision and pattern recognition, 2008: 1-8 P
[109] J.Lafferty, A.McCallum, F.Pereira. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In Proceedings of the International Conference on Machine Learning[C]. 2001, 18: 282-289 P
[110] T.Toyoda, O.Hasegawa. Random field model for integration of local information and global information[J]. Pattern Analysis and Machine Intelligence. 2008, 30(8): 1483-1489 P
[111] S.Kumar, M.Hebert. Discriminative Random Fields[J]. International Journal of Computer Vision (IJCV). 2006, 68(2): 179-201 P
[112] A.Quattoni, S.Wang, L.P.Morency. Hidden Conditional Random Fields[J].IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007, 29(10):1848-1852 P
[113] S.Kumar, M.Hebert. A hierarchical field framework for unified context-based classification[C]. In Proceedings of the IEEE Conference on Computer Vision. ICCV2005 (2): 1284-1291 P
[114] Y.Wang, Q.Ji. A Dynamic Conditional Random Field Model for Object Segmentation in Image Sequences[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR05). 2005: 264-270 P
[115] X.Geng,J.Zhao. Interactive Image Segmentation with Conditional Random Fields[C]. The 4th International Conference on Natural Computation ICNC08 . 2008: 25-27 P
[116]禇一平.基于条件随机场模型的视频目标分割算法研究[D].浙江大学. 2007:33-59页
[117]黄天羽,石崇德,李凤霞等.一种基于判别随机场模型的联机行为识别方法[J].计算机学报. 2009, 32(02):275-280页
[118]潘晓雯.人体运动捕捉数据的检索[D].大连理工大学. 2009: 1-21页
[119] N.Plath, M.Toussaint, S.Nakajima, Multi-class image segmentation using Conditional Random Fields and Global Classification[C]. Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009: 817-824 P
[120] J.Reynolds, K.Murphy. Figure-ground segmentation using a hierarchical conditional random field. Proceedings of the Fourth Canadian Conference on Computer and Robot Vision(CVR) 2007:175-182 P
[121] X. He, R. Zemel, and M. Carreira-Perpinan. Multiscale conditional random fields for image labelling[C]. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2004: 695–702 P
[122] P.Schnitzspan, M.Fritz, B. Schiele. Hierarchical Support Vector RandomFields: Joint Training to Combine Local and Global Features. In Proc. ECCV, 2008: 527-540 P
[123] P.Zhong, R.Wang. A multiple conditional random fields ensemble model for urban area detection in remote sensing optical images[J]. IEEE Transactions on Geoscience and Remote Senssing. 2007, 45(12): 3978-3988P
[124] G.Tsechpenakis, D.N.Metaxas. CRF-driven Implicit Deformable Model[C]. IEEE Conference on Computer Vision and Pattern Recognition. 2007: 1-8 P
[125] U.Vovk, F. Pernus, B. Likar. A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans. Med. Imag[J]. 2007, 26(3): 405-421 P
[126] C. Li, C.Kao, J.Gore, Z.Ding. Implicit active contours driven by local binary fitting energy[C]. IEEE Conference on CVPR, 2007:1-6 P
[127] C. Studholme, V. Cardenas, E. Song, et al.. A. Maudsley et al.. Accurate template-based correction of brain MRI intensity distortion with application to dementia and aging[J]. IEEE Trans. Med Imag., 2004, 23 (1):99–110 P
[128] J.Luo, Y.Zhu, P.Clarysse et al.. Correction of bias field in MR images using singularity function analysis[J]. IEEE Trans. Med. Imag. 2005, 24(8): 1067–1085 P
[129] M.N.Ahmed, S.M.Yamany, A.Farag et al.. A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data[J]. IEEE Trans Med Image. 2002, 21(3): 193–199 P
[130] W.Wells, E.Grimson, R.Kikinis, et al.. Adaptive segmentation of MRI data. IEEE Trans. Med. Imag. 1996, 15(4): 429-442 P
[131] D.Pham, J.Prince. Adaptive fuzzy segmentation of magnetic resonance images[J]. IEEE Trans. Med. Imag. 1999:18(9), 737-752 P
[132] K.Leemput, F.Maes, D.Vandermeulen, P.Suetens. Automated model-based bias field correction of MR images of the brain[J]. IEEE Trans. Med. Imag. 1999, 18(10), 885–896 P
[133]窦丽莉.基于吸引力传播算法的脑核磁共振图像分割[D].东北师范大学. 2009: 15-23页
[134]车娜.基于局部模糊聚类的脑组织核磁共振图像分割方法[D].东北师范大学. 2008: 13-20页
[135] C.Li, C.Gatenby, L.Wang et al.. A Robust Parametric Method for Bias Field Estimation and Segmentation of MR Images. IEEE conference CVPR 2009: 218-223 P
[136] L.Wang,etal.,Active contours driven by local Gaussian distribution fitting energy, Signal Processing. 2009, 89(12): 2435-2447 P
[137]王利,陈允杰,汤杨等.一种基于遗传算法的脑MR图像去偏移场模型[J].中国图象图形学报. 2008, 13(17):1281-1285页
[138] T.Chan, S.Esedoglu, M.Nikolova. Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models[J]. SIAM Journal on Applied Mathematics , 2006, 66(5) :1632-1648 P
[139] X.Bresson, S.Esedoglu, P.Vandergheynst, J.Thiran, et al.. Fast Global Minimization of the Active Contour/Snake Model[J]. Journal of Mathematical Imaging and Vision. 2007,37(4):123-137 P
[140] L.Cohen, R.Kimmel. Global Minimum for Active Contour Models: A Minimal Path Approach[J]. International Journal of Computer Vision, 1997, 24(1): 57-78 P
[141] B.Appleton, H.Talbot. Globally Optimal Geodesic Active Contours[J]. Journal of Mathematical Imaging and Vision, 2005, 23(1):67-86 P
[142] T.Brox. From pixels to regions: Partial differential equations in image analysis[D]. Germany, Saarland University, 2005: 30-78 P
[143]孙家柄.遥感原理与应用[M].武汉大学出版社,2009:1-57页
[144] R.O.Duda, P.E.Hart, D.G.Stork. Pattern Classification,Second Edition[M]. John Wiley & sons,Inc., 2009:1-90 P
[145]谭琨,杜培军.基于支持向量机的高光谱遥感图像分类[J].红外与毫米波学报. 2008, 27(2): 123-128页
[146]韩敏,林晓峰.一种基于Wedgelet变换的遥感图像分类算法[J].红外与毫米波学报. 2008, 27(4): 280-284页
[147]赵春晖,朱志球.二进脊波变换的高光谱遥感图像融合分类[J].哈尔滨工程大学学报. 2008, 29(11): 1222-1226页
[148]邓良基.遥感基础与应用[M].中国农业出版社. 2003:1-48页
[149]曹建农.基于可分解马尔科夫网的图像分割方法研究[D].武汉大学, 2005:30-46页
[150]葛宏立.面向类的图像分割方法研究[D].北京林业大学, 2004:27-51页
[151] G.A.Babich, O.I.Camps. Weighted parzen windows for pattern classification[J]. IEEE Trans. Pattern Anal. Mach. Intell. 1996, 18: 567–570.
[152] V.S.Vyas, P.Rege. Automated texture analysis with Gabor filters[J]. GVIP Journal, 2006, 6:35-41 P
[153]刘旭拢,何春阳,潘耀忠等.遥感图像分类精度的点、群样本检验与评估[J].遥感学报, 2006, 10(3): 366-372页
[154] ENVI EX User's Guide[ EB/ OL ] . https://www.ittvis.com/, 2005:1-38 P
[155] F.Melgani, L.Bruzzone. Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004,42:178-1790 P
[156] C.P.Lee. Robust Image Segmentation using Active Contours: Level Set Approaches[D]. PhD Dissertation, North Carolina State University, 2005:38-59 P
[157] G.J.Hay, G.Castilla. Object-based image analysis: Strengths, weaknesses, opportunities and threats (SWOT)[C]. 1st International Conference on Object-based Image Analysis (OBIA), 2006:1-6 P
[158]张秀英,冯学智,江洪.面向对象分类的特征空间优化[J].遥感学报, 2009, 13(4):664-667页
[159] Definiens Imaging GmbH. eCognition User Guide[EB/OL]. Definiens Imaging GmbH. Germany. http://www.definiens-imaging.Com, 2003:1-20 P
[160] D.Comaniciu, P.Meer. Mean shift: a robust approach toward feature space analysis[J]. IEEE Trans. Pattern Anal. Machine Intell.. 2002, 24(5): 603–619.
[161] S.Gould, J.Rodgers, D.Cohen, et al.. Multi-Class Segmentation with Relative Location Prior[J]. International Journal of Computer Vision. 2008, 80(3): 300-316 P
[162]杨国鹏,余旭初,陈伟,刘伟.基于核Fisher判别分析的高光谱遥感影像分类[J].遥感学报. 2008, 12(04): 579-584页
[163] S.V.N.Vishwanathan, N.Schraudolph, M.Schmidt, et al.. Accelerated Training Conditional Random Fields with Stochastic Gradient Methods[C]. In Proc. Intl. Conf. Machine Learning, 2006: 969-976 P
[164] N.N.Schraudolph. Fast curvature matrix-vector products for second-order gradient descent[J]. Neural Computation. 2002, 14(7):1723–1738 P
[165] J.S.Yedidia, W.T.Freeman, Y.Weiss. Understanding Belief Propagation and Its Generalizations[M]. Exploring Artificial Intelligence in the New Millennium, 2003: 239-236 P
[166] Y.Shi, W.C.Karl. A fast level set method without solving PDEs[C]. in:Proceedings of IEEE Intenational Conference on Acoustics Speech and Signal Processing, 2005, 2:97-100 P
[167]徐盛,李志斌.基于AOS格式的扩展Chan-Vese模型及多水平集图像分割方法[J].华东师范大学学报(自然科学版). 2006, 3: 66-70页
[168] G. Papandreou,P. Maragos. A Fast Multigrid Implicit Algorithm for the Evolution of Geodesic Active Contours[J]. Proceedings of IEEE Intenational Conference on Computer Vision and Pattern Recognition (CVPR), 2004:1-6 P
[169] H.Li, A.Yezzi. Local or Global Minima: Flexible Dual-Front Active Contours[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007, 29(1): 1-14 P
[170]余瑞星,李言俊,张科.利用对数极坐标的快速水平集算法[J].光电工程. 2006,33(5): 71-75页
[171]王振华,陈杰,窦丽华.水平集曲线演化快速提取足迹轮廓[J].计算机辅助设计与图形学学报. 2007,19(10):1269-1273页
[172]李晓峰,张树清,刘强.高分辨率遥感影像的快速分割方法[J].红外与毫米波学报. 2009,28(2):146-150页
[173]翁建广,庄越挺,潘云鹤.基于改进稀疏场算法的水平集形状过渡[J].软件学报. 2006,(07):1544-1551页