High Robust Tongue Image Segmentation Algorithm Based on Active Contour Model With Shape Priors
-
摘要: 中医舌图像分割一直面临着由于采集设备更新换代等因素带来的分割方法鲁棒性下降的问题.提出一种基于形状先验主动轮廓模型的中医舌图像分割方法.首先, 采用统计方法获得大致舌体图像;然后, 采用形状先验水平集方法得到基本完整的舌体;最后, 采用Snake模型方法得到最终准确分割结果.实验结果表明:该方法对于不同环境下得到的舌图像分割都具有良好的分割效果.Abstract: There always exits a problem with the tongue image segmentation that the robustness of the method decreases as the hardware is replaced or upgraded.In this paper, a novel tongue image segmentation method is proposed based on active contour model with shape priors.The statistical method is used to get a rough result, then the level set method with shape priors is used to get a mostly complete tongue, and the exact tongue is finally obtained using a post-processing step.Experimental results show that accurate segmentation can be obtained with the proposed method for different tongue image acquisition environments.
-
Keywords:
- tongue segmentation /
- statistical chromaticity /
- shape prior /
- level set /
- Snake model
-
-
[1] 沈兰荪, 蔡轶珩, 张新峰.中医舌象的采集与分析[M].北京:北京工业大学出版社, 2007. [2] 赵忠旭, 王爱民, 沈兰荪.基于数学形态学和HIS模型的彩色舌图像分割[J].北京工业大学学报, 1999, 25 (2) :67-71.ZHAO Zhong-xu, WANG Ai-min, SHEN Lan-sun.The colortongue image segmentation based on mathematical morphologyand HIS model[J].Journal of Beijing University ofTechnology, 1999, 25 (2) :67-71. (in Chinese) [3] 刘关松, 徐建国, 高敦岳.舌图像自动分割方法[J].计算机工程, 2003, 29 (12) :63-64.LIU Guan-song, XU Jian-guo, GAO Dun-yue.Anautomatic approach for tongue image segmentation[J].Computer Engineering, 2003, 29 (12) :63-64. (inChinese) [4] 王艳清.中医舌象分析仪集成化研究[D].北京:北京工业大学电子信息与控制工程学院, 2003.WANG Yan-qing.Research on the integration of tongueimaging and analysis instrument[D].Beijing:College ofElectronic Information and Control Engineering, BeijingUniversity of Technology, 2003. (in Chinese) [5] 覃武星, 李斌, 岳小强.一种基于初始化Snake轮廓线的混合舌图像分割算法[J].中国科学技术大学学报, 2010, 40 (8) :807-811.QIN Wu-xing, LI Bin, YUE Xiao-qiang.A hybrid tongueimage segmentation algorithm based on initialization ofsnake contours[J].Journal of University of Science andTechnology of China, 2010, 40 (8) :807-811. (inChinese) [6] 孙炀, 罗瑜, 周昌乐, 等.一种基于分裂-合并方法的中医舌像区域分割算法及其实现[J].中国图象图形学报, 2003, 8 (12) :1395-1399.SUN Yang, LUO Yu, ZHOU Chang-le.A method basedon split-combining algorithm for the segmentation of theimage of tongue[J].Journal of Image and Graphics, 2003, 8 (12) :1395-1399. (in Chinese) [7] 王郁中, 杨杰, 周越, 等.一种舌图像中舌体的自动提取方法[J].计算机仿真, 2005, 22 (2) :232-235.WANG Yu-zhong, YANG Jie, ZHOU Yue.Automatictongue area extraction in tongue images[J].ComputerSimulation, 2005, 22 (2) :232-235. (in Chinese) [8] 杨大生, 陈晖, 邹丰美, 等.一种有效的舌体自动化分割方法[J].计算机应用研究, 2007, 24 (2) :170-172.YANG Da-sheng, CHEN Hui, ZOU Feng-mei.Effectivealgorithm on automatic segmentation of body of tongue[J].Application Research of Computers, 2007, 24 (2) :170-172. (in Chinese) [9] TSAI A, YEZZI A, WELLS W, et al.A shape-basedapproach to the segmentation of medical imagery usinglevel sets[J].IEEE Trans On Medical Imaging, 2003, 22:137-154.
[10] PARAGIOS N, ROUSSON M, RAMESH V.Matchingdistance function:a shape-to-area variational approach forglobal-to-local registration[C]∥European Conference inComputer Vision, Copenhangen, Denmark, May 28-31, 2002.
[11] ROUSSON M, PARAGIOS N.Shape priors for level setrepresentations[C]∥European Conference in ComputerVision, Copenhangen, Denmark, May 28-31, 2002.
[12] LEVENTON M, GRIMSON E, FAUGERAS O.Statisticalshape influence in geodesic active contours[J].Computer Vision and Pattern Recognition, 2000, 1:316-323.
[13] CHEN Y, TAGARE H, THIRUVENKADAM S, et al.Using prior shapes in geometric active contours in avariational framework[J].International Journal ofComputer Vision, 2002, 50 (3) :315-328.
[14] CHAN T, VESE L.Active contours without edges[J].IEEE Transaction on Image Processing, 2001, 10 (2) :266-277.
[15] CHAN T, ZHU W.Level set based shape priorsegmentation[C]∥IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition, San Diego, June 20-26, 2005, 2:1164-1170.
[16] CREMERS D, OSHER S, SOATTO S.Kernel densityestimation and intrinsic alignment for shape priors in levelset segmentation[J].International Journal of ComputerVision, 2006, 69 (3) :335-351.
[17] CHEN S, RADKE R J.Level set segmentation with bothshape and intensity priors[C]∥IEEE 12th InternationalConference on Computer Vision, Kyoto, Japan, September27-October 4, 2009:763-770.
计量
- 文章访问数: 12
- HTML全文浏览量: 1
- PDF下载量: 8