基于活动轮廓模型的图像分割算法综述

doi:10.3969/j.issn.0258-8021. 2015. 04.009

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (841 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要活动轮廓模型是一种重要的图像分割技术，它利用底层信息，并结合高层先验知识，实现对复杂目标轮廓的自动分割。自Kass等提出该思想以来的20多年中，活动轮廓模型在理论研究和应用方面均取得长足发展。首先，介绍活动轮廓模型的发展历程，重点阐述并分析典型的参数活动轮廓模型和几何活动轮廓模型，进而扼要介绍混合活动轮廓模型和快速求解算法；随后，从理论基础、分割效果、算法效率以及应用等方面，比较两类模型之间的区别与联系；最后，对活动轮廓模型未来的发展趋势进行展望。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：活动轮廓模型, 图像分割, 参数活动轮廓模型, 几何活动轮廓模, 混合活动轮廓模型

Abstract：Active contour model is an important method for image segmentation. It combines underlying information with highlevel prior knowledge to achieve automatic segmentation for complex objects. Active contour model has been developed greatly in theory research and application, since it was proposed twenty years ago. This paper reviewed the development process of active contour model at first and describes the classical parametric active contour models and geometric active contour models, and presents briefly new hybrid active contour models as well as fast solution algorithms. After that, the relationship between these two kinds of models through theory basis, performance, efficiency and applications were introduced. The future prospect of active contour model was discussed as well.

Key words： active contour model image segmentation parametric active contour model geometric active contour model hybrid active contour model

基金资助:国家“十二五”科技支撑计划资助项目（2012BAI10B04）；国家自然科学基金(81101903)

引用本文:

段丁娜¹张欢¹邱. 基于活动轮廓模型的图像分割算法综述[J]. 中国生物医学工程学报, 2015, 34(4): 445-454.
Duan Dingna¹Zhang Huan¹Qiu Chenhui¹Xia Shunren^1,2#*. A Review of Active Contour Model Based Image Segmentation Algorithms. journal1, 2015, 34(4): 445-454.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2015. 04.009 或 http://cjbme.csbme.org/CN/Y2015/V34/I4/445

［1］Marr D. A computational investigation into the human representation and processing of visual information ［M］. San Francisco: W H Freeman and Company, 1982.
［2］李培华，张田文. 主动轮廓线模型(蛇模型)综述［J］. 软件学报, 2000, 11(6): 751-757.
［3］Li Chunming, Kao CY, Gore J, et al. Minimization of regionscalable fitting energy for image segmentation ［J］. IEEE Transactions on Image Processing, 2008, 17(10): 1940-1949.
［4］Kass M, Witkin A, Terzopoulos D. Snakes: active contour models ［J］. International Journal of Computer Vision, 1988, 1(4): 321-331.
［5］Caselles V, Kimmel R, Sapiro G. Geodesic active contours ［J］. International Journal of Computer Vision, 1997, 22(1): 61-79. 
［6］Malladi R, Sethian JA, Vemuri BC. Shape modeling with front propagation: a level set approach ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(2): 158-175.
［7］Cohen LD. On active contour models and balloons ［J］. CVGIP: Image Understanding, 1991, 53(2): 211-218.
［8］Xu Chenyang, Prince JL. Snakes, shapes, and gradient vector flow ［J］. IEEE Transactions on Image Processing, 1998, 7(3): 359-369.
［9］Xu Chenyang, Prince JL. Generalized gradient vector flow external forces for active contours ［J］. Signal Processing, 1998, 71(2): 131-139.
［10］张丽飞，王东峰，时永刚，等. 基于形变模型的图像分割技术综述［J］. 电子与信息学报, 2003, 25(3): 395-403.
［11］Hafiane A, Vieyres P, Delbos A. Phasebased probabilistic active contour for nerve detection in ultrasound images for regional anesthesia ［J］. Computers in Biology and Medicine, 2014, 52(1): 88-95.
［12］Ma Li, Su Tianzhen. Contour extraction of skin tumors using visual attention and GVFsnake model ［J］. Engineering, 2013, 5(10): 482-486.
［13］Rodtook A, Makhanov SS. Multifeature gradient vector flow snakes for adaptive segmentation of the ultrasound images of breast cancer ［J］. Journal of Visual Communication and Image Representation, 2013, 24(8): 1414-1430.
［14］Ko BC, Gim JW, Nam JY. Automatic white blood cell segmentation using stepwise merging rules and gradient vector flow snake ［J］. Micron, 2011, 42(7): 695-705.
［15］Leroy B, Herlin IL, Cohen LD. Multiresolution algorithms for active contour models ［C］ //Berger MO, Deriche R, eds. The 12th International Conference on Analysis and Optimization of Systems Images, Wavelets and PDEs. Paris: Springer Berlin Heidelberg, 1996: 58-65.
［16］Cohen LD, Cohen I. Finiteelement methods for active contour models and balloons for 2\|D and 3\|D images ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 11(15): 1131-1147.
［17］Szeliskit R, Terzopoulos D. Physicallybased and probabilistic models for computer vision ［C］ //Vemuri BC,
eds. SPIE: Geometric Methods in Computer Vision. San Diego: Society of PhotoOptical Instrumentation Engineers, 1991: 140-152.
［18］Storvik G. A Bayesian approach to dynamic contours through stochastic sampling and simulated annealing ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(10): 970-986.
［19］Osher S, Sethian JA. Fronts propagating with curvature dependent speed: algorithms based on Hamilton
\|Jacobi formulations ［J］. Journal of Computational Physics, 1988, 79(1): 12-49.
［20］Mumford D, Shah J. Optimal approximation by piecewise smooth function and associated variational problems ［J］. Communication on Pure and Applied Mathematics, 1989, 42(5): 577-685.
［21］Chan TF, Vese LA. Active contours without edges ［J］. IEEE Transactions on Image Processing, 2001, 10(2): 266-277.
［22］Vese LA, Chan TF. A multiphase level set framework for image segmentation using the mumford and shah model ［J］. International Journal of Computer Vision, 2002, 50(3): 271-293.
［23］Tsai A, Yezzi Jr A, Willsky AS. Curve evolution implementation of the mumfordshah functional for image segmentation, denoising, interpolation, and magnification ［J］. IEEE Transcations on Image Processing, 2001, 10(8): 1169-1186.
［24］Li Chunming, Kao CY, Gore JC, et al. Implicit active contours driven by local binary fitting energy ［C］ //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 1-7.
［25］Wang Li, He Lei, Mishra A, et al. Active contours driven by local Gaussian distribution fitting energy ［J］. Signal Processing, 2009, 89(12): 2435-2447.
［26］Zhang Kaihua, Song Huihui, Zhang Lei. Active contours driven by local image fitting energy ［J］. Pattern Recognition, 2010, 43(4): 1199-1206.
［27］He Chuanjiang, Wang Yan, Chen Qiang. Active contours driven by weighted regionscalable fitting energy based on local entropy ［J］. Signal Processing, 2012, 92(2): 587-600.
［28］Lankton S, Tannenbaum A. Localizing regionbased active contours ［J］. IEEE Transactions on Image Processing, 2008, 17(11): 2029-2039.
［29］Li Bingnan, Chui CK, Chang S, et al. Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation ［J］. Computers in Biology ad Medicine, 2011, 41(1): 1-10.
［30］Michailovich O, Rathi Y, Tannenbaum A. Image segmentation using active contours driven by the Bhattacharyya gradient flow ［J］. IEEE Transactions on Image Processin, 2007, 16(11): 2787-2801.
［31］Papandreou G, Maragos P. Multigrid geometric active contour models ［J］. IEEE Transactions on Image Processing, 2000，16(1): 229-240.
［32］Zhang Kaihua, Zhang Lei, Song Huihui, et al. Active contours with selective local or global segmentation: A new formulation and level set method ［J］. Image and Vision Computing, 2010, 28(4): 668-676.
［33］Pi Ling, Shen Chaoming, Li Fang, et al. A variational formulation for segmenting desired objects in color images ［J］. Image and Vision Computing, 2007, 25(9): 1414-1421.
［34］Liu Liman, Tao Wenbing, Liu Jin, et al. A variational model and graph cuts optimization for interactive foreground extraction ［J］. Signal Processing, 2011, 91(5): 1210-1215. 
［35］,Zheng Qiang, Dong Enqing, Cao Zhulou, et al. Modified localized graph cuts based active contour model for local segmentation with surrounding nearby clutter and intensity inhomogeneity ［J］. Signal Processing, 2013, 93(4): 961-966. 
［36］Dong Enqing, Zheng Qiang, Sun Wenyan, et al. Constrained multiplicative graph cuts based active contour model for magnetic resonance brain image series segmentation ［J］. Signal Processing, 2014, 104: 59-69. 
［37］ Tian Yun, Duan Fuqing, Zhou Mingquan, et al. Active contour model combining region and edge information ［J］. Machine Vision and Applications, 2013,24(1): 47-61.
［38］Song Chunzhu, Yuille A. Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation ［J］. IEEE Transactions on Patteren Analysis and Machine Intelligence, 1996, 18(9): 884-900.
［39］Chakraborty A, Staib LH, Duncan JS. Deformable boundary finding in medical images by integrating gradient and region information ［J］. IEEE Transactions on Image Processing, 1996, 15（(6): 859-870.
［40］Paragios N, Deriche R. Geodesic active regions and level set methods for supervised texture segmentation ［J］. International Journal of Computer Vision, 2002, 46(3): 223-247.［41］Caselles V, Catté F, Coll T, et al. A geometric model for active contours in image processing ［J］. Numerische Mathematik, 1993, 66(1): 1-31.
［42］Sethian JA. A fast marching level set method for monotonically advancing fronts ［J］. Proceedings of the National Academy of Sciences, 1996, 934): 1591-1595.
［43］Weickert J, Romeny BMTH, Viergever MA. Efficient and reliable schemes for nonlinear diffusion filtering ［J］. IEEE Transactions on Image Processing, 1998, (73): 398-410.
［44］Boykov Y, Kolmogorov V. Computing geodesics and minimal surfaces via graph cuts ［C］ //Proceedings of the 9th IEEE International Conference on Computer Vision. Nice: IEEE, 2003: 26-33.
［45］Boykov Y, Kolmogorov V, Cremers D, et al. An integral solution to surface evolution PDEs via geocuts ［C］ //Leonardis A, Bischof H, Pinz A, eds. Proceedings of the 9th European Conference on Computer Vision. Graz: Springer Berlin Heidelberg, 2006: 409-422.
［46］Xu Ning, Bansal R, Ahuja N. Object segmentation using graph cuts based active contours ［C］ //Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison: IEEE, 2003: 46-53.
［47］Xu Ning, Ahuja N, Bansal R. Object segmentation using graph cuts based active contours ［J］. Computer Vision and Image Understanding, 2007, 107(3): 210-224.
［48］Tao Wenbing. Iterative narrowbandbased graph cuts optimization for geodesic active contours with region forces (GACWRF) ［J］. IEEE Transactions on Image Processing, 2012, 21(1): 284-296.
［49］Chen Cheng, Li Houqiang, Zhou Xiaobo, et al. Constraint factor graph cutbased active contour method for automated cellular image segmentation in RNAi screening ［J］. Journal of Microscopy, 2008, 230(2): 177-191.
［50］El-Zehiry N, Elmaghraby A. A graph cut based active contour without edges with relaxed homogeneity constraint ［C］ //The 19th International Conference on Pattern Recognition. Tampa: IEEE, 2008: 1-4.
［51］El-Zehiry N, Xu S, Sahoo P, et al. Graph cut optimization for the MumfordShah model ［C］ //Villanueva JJ, eds. Proceedings of the 7th IASTED International Conference Visualization, Imaging, and Image Processing. Anaheim: ACTA Press, 2007: 182-187. 
［52］Xu Chengyang, Yezzi Jr A, Prince JL. On the relationship between parametric and geometric active contours ［C］ //Conference Record of the 34th Asilomar Conference on Signals, Systems, and Computers. Pacific Grove: IEEE, 2000: 483-489.
［53］Nguyen K, Fookes C, Sridharan S. Fusing shrinking and expanding active contour models for robust iris segmentation ［C］ //Proceedings of the 10th International Conference on Information Sciences Signal Processing and their Applications(ISSPA). Kuala Lumpur: IEEE, 2010: 185-188.
［54］Al-Diri B, Hunter A, Steel D. An active contour model for segmenting and measuring retinal vessels ［J］. IEEE Transactions on Medical Imaging, 2009, 28(9): 1488-1497.
［55］孙丰荣，刘泽，李艳玲，等. 一种改进的自适应形变模型及其血管内超声图像边缘提取应用［J］. 中国生物医学工程学报, 2008, 27(2): 276-281.
［56］Smith MB, Li Hongsheng, Shen Tian, et al. Segmentation and tracking of cytoskeletal filaments using open active contours ［J］. Cytoskeleton, 2010, 67(11): 693-705.
［57］Abdoli M, Dierckx R, Zaidi H. Contourletbased active contour model for PET image segmentation ［J］. Medical Physics, 2013, 40(8): 082507.
［58］Zhu Wei, Kang SH, Biros G. A geodesicactivecontourbased variational model for shortaxis cardiac MR image segmentation ［J］. International Journal of Computer Mathematics, 2013, 〖STHZ〗90〖STBZ〗(1): 124-139. 
［59］Qian Xiaohua, Wang Jiahui, Guo Shuxu, et al. An active contour model for medical image segmentation with application to brain CT image ［J］. Medical Physics, 2013, 40(2): 021911. 
［60］Foruzan AH, Chen Yenwei, Zoroofi RA, et al. Segmentation of liver in lowcontrast images using Kmeans clustering and geodesic active contour algorithms ［J］. IEICE Transactions on Information and Systems, 2013, 96(4): 798-807.
［61］Hao Xin, Shen Ye, Xia Shunren. Automatic mass segmentation on mammograms combining random walks and active contour ［J］. Journal of Zhejiang University Science C, 2012, 13〖STBZ〗(9): 635-648.
［62］Ahmadi S, Zoej MJ, Ebadi H, et al. Automatic urban building boundary extraction from high resolution aerial images using an innovative model of active contours ［J］. International Journal of Applied Earth Observation and Geoinformation, 2010, 12(3): 150-157.
［63］Celik T, Ma Kaikuang. Multitemporal image change detection using undecimated discrete wavelet transform and active contours ［J］. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(2): 706-716.
［64］Hu Weiming, Zhou Xue, Li Wei, et al. Active contourbased visual tracking by integrating colors, shapes, and motions ［J］. IEEE Transactions on Image Processing, 2013, 22(5): 1778-1792.