计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 314-319.doi: 10.11896/j.issn.1002-137X.2017.05.058
• 图形图像与模式识别 • 上一篇
汪梅,李琳,汪斌,何高明
WANG Mei, LI Lin, WANG Bin and HE Gao-ming
摘要： 主动轮廓模型(snake模型)被广泛应用于边缘提取、图像分割等领域。该模型能对目标适当初始化,并进行自主收敛,使得能量处于极小值状态,以达到目标分离的效果。当目标初始位置敏感时,需要依赖其他机制对内部能量进行合理初始化,由于模型的非凸性,它有可能收敛到局部极值点甚至发散。将分水岭算法应用于主动轮廓模型的能量分割算法,通过改进的分水岭算法确定主动轮廓模型的初始轮廓,利用迭代完成对轮廓点周围的局部近邻点的检索,以选取更小的轮廓模型,当获得最小值时完成目标轮廓的提取。
| [1] LI X P,WANG X.Active contour model-based medical image segmentation method collaborative with fuzzy C-means[J].Chinese Journal of Scientific Instrument,2013,4(4):860-865.(in Chinese) 李宣平,王雪.模糊聚类协作区域主动轮廓模型医学图像分割[J].仪器仪表学报,2013,4(4):860-865. [2] CUI B X,ZHANG K,GUO Y.Image segmentation algorithm combining minimum interclass variance with region growing[J].Journal of Shenyang University of Technology,2008,0(5):568-571.(in Chinese) 崔宝侠,张昆,郭宇.最小类内方差和区域生长相结合的图像分割法[J].沈阳工业大学学报,2008,0(5):568-571. [3] LIU L X,MA Z M,ZHAO H B,et al.A Method for Segmenting Cardiac Magnetic Resonance Images Using Active Contours[J].Chinese Journal of Computers,2012,35(1):146-153.(in Chinese) 刘利雄,马忠梅,赵恒博,等.一种基于主动轮廓模型的心脏核磁共振图像分割方法[J].计算机学报,2012,5(1):146-153. [4] COHEN L D.On Active Contour Models and Balloons[J].Cvgip:Image Understanding,1991,3(2):211-218. [5] XU C Y,PRINCE J L.Snakes,shapes and gradient vector flow[J].IEEE Transactions on Image Processing,1998,7(3):359-369. [6] YANG J,TANG S,NEO S Y.An Improved Snake Algorithm Based on Global Contour Deformation[J].Natural Science Journal of Xiangtan University,2008,0(1):135-140.(in Chinese) 杨旌,唐胜,NEO S Y.结合全局轮廓变形的改进Snake算法[J].湘潭大学自然科学学报,2008,0(1):135-140. [7] WU Y Y,YUE X K.Image Segmentation for Space Target Ba-sed-on Watershed Algorithm[J].Computer Simulation,2010,8(2):300-303.(in Chinese) 武媛媛,岳晓奎.基于分水岭算法的空间目标图像分割方法[J].计算机仿真,2010,8(2):300-303. [8] KASS M,WITKIN A,TERZOPOULOS D.Snake:Active contour models[J].International Journal of Computer Vision,1988,1(4):321-331. [9] REN S G,MA C,XU H L.Improved Skeleton Extracton Algorithm Based Active Contour Model Research[J].Computer Scien-ce,2013,40(7):289-296.(in Chinese) 任守纲,马超,徐焕良.基于改进主动轮廓模型的图像分割方法研究[J].计算机科学,2013,0(7):289-296. [10] LIU J L,SUI Q M,ZHU W X.MR image segmentation based on probability density function and active contour model[J].Optics and Precision Engineering,2014,22(12):3435-3443.(in Chinese) 刘建磊,隋青美,朱文兴.结合概率密度函数和主动轮廓模型的磁共振图像分割[J].光学精密工程,2014,2(12):3435-3443. [11] HU T S,XIANG F Y.Research on initial contour selection of snake model based on watershed algorithm[J].Ournal of Z hengjiang University of Technology,2008,36(4):347-377.(in Chinese) 胡同森,项方云.使用标识分水岭算法确定Snake模型的初始轮廓[J].浙江工业大学学报,2008,6(4):347-377. [12] SHEN J,YANG X Z.A Novel Segmentation Algorithm Based on Edge-Preserving Watershed[J].Journal of Engineering Gra-phics,2009(5):81-88.(in Chinese) 沈晶,杨学志.一种新的边缘保持分水岭的图像分割算法[J].工程图学学报,2009(5):81-88. [13] TAN H B,HOU Z Q,LIU R,et al.Watershed Algorithm for Color Image Segmentation Based on Adaptive Marker-extraction[J].Computer Engineering,2010,6(19):229-231.(in Chinese) 谭洪波,侯志强,刘荣,等.基于自适应标记提取的分水岭彩图分割算法[J].计算机工程,2010,6(19):229-231. [14] YANG S Q,NING J F,HE D J.Image segmentation algorithm of touching rice kernels based on active contour model[J].Transactions of the CSAE,2010,26(2):207-211.(in Chinese) 杨蜀秦,宁纪锋,何东健.一种基于主动轮廓模型的连接米粒图像分割算法[J].农业工程学报,2010,26(2):207-211. [15] WANG Y,JIA Y,LIU L.Harmonic gradient vector flow external force for snake model[J].Electronics Letters,2008,4(2):105-106. [16] LANKTO S,TANNENBAUM A.Localizing Region-based Active Contours[J].IEEE Tranasactions on Image Processing,2008,1(17):2029-2039. [17] SHANG Y F,WANG N,WANG H.Medical object extraction model based on regional energy minimization and active contour model[J].Application Research of Computers,2012,9(7):2715-2718.(in Chinese) 尚岩峰,汪宁,汪辉.基于区域能量最小和主动轮廓模型的医学目标提取[J].计算机应用研究,2012,9(7):2715-2718. [18] ZHANG W.Markov Random Field Based Object Segmentation Combining Edge and Shape Prior[J].Journal of Chongqing University of Technology (Natural Science),2014,8(10):79-85.(in Chinese) 张微.融合边缘和形状先验的MRF目标分割[J].重庆理工大学学报(自然科学),2014,8(10):79-85. |
| No related articles found! |
|
||
首页