基于改进CV模型的图像分割算法Image segmentation algorithm based on improved CV model
鲁圆圆,强静仁,汪朝
摘要(Abstract)：
传统CV模型在目标图像存在噪声干扰及图像背景较为复杂的情况下,图像分割效果较差,极易造成误分割。为了提高基于CV模型图像分割的分割效果及分割效率,提出一种基于改进CV模型的图像分割算法。首先,根据曲线演化理论对CV模型的曲线驱动力进行简化,以此提高模型的分割效率;然后,利用L1范数构造CV模型的能量泛函,同时引入中值替代传统CV模型中的曲线拟合中心,在简化数据计算的同时,提高模型对噪声的鲁棒性;最后,将该曲线驱动力与L1范数能量泛函进行融合,以此构造最终的改进CV模型的能量泛函。将所提模型与传统CV模型、LIF模型、局部二值模型以及偏置场修正水平集模型的实验结果进行对比,结果表明所提模型分割效果最优,且分割速率最高。
关键词(KeyWords)： 图像分割;改进型CV模型;曲线驱动力;L1范数能量泛函;分割效率;数据计算
基金项目(Foundation): 国家自然科学基金青年科学基金(51404182)~~
作者(Author): 鲁圆圆,强静仁,汪朝
DOI: 10.16652/j.issn.1004-373x.2018.21.016
参考文献(References)：
- [1]崔玉玲.基于改进符号距离函数的变分水平集图像分割算法[J].模式识别与人工智能,2013,26(11):1033-1040.CUI Yuling. Variational level set image segmentation algorithm based on improved symbol distance function[J]. Pattern recognition and artificial intelligence,2013,26(11):1033-1040.
- [2] WANG Hui,HUANG Tingzhu,XU Zhi,et al. A two-stage image segmentation via global and local region active contours[J].Neurocomputing,2016,205(C):130-140.
- [3] LI Chunming,XU Chenyang,GUI Changfeng,et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE transactions on image processing,2010,19(12):3243-3254.
- [4]黄扬,郭立君,张荣.融合全局和局部相关熵的图像分割[J].中国图象图形学报,2015,20(12):1619-1628.HUANG Yang,GUO Lijun,ZHANG Rong. Image segmentation with global and local correlation entropy[J]. Chinese journal of image and graphics,2015,20(12):1619-1628.
- [5] CASELLES V,KIMMEL R,SAPIRO G. Geodesic active contours[J]. International journal of computer vision,1997,22(1):61-79.
- [6] LI Chunming,GATENBY Chris,WANG Li,et al. A robust parametric method for bias field estimation and segmentation of MR images[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami:IEEE,2009:218-223.
- [7] CHAN T F,VESE L A. Active contours without edges[J].IEEE transactions on image processing,2001,10(2):266-277.
- [8]张开华,周文罡,张振,等.一种改进的CV主动轮廓模型[J].光电工程,2008,35(12):112-116.ZHANG Kaihua,ZHOU Wengang,ZHANG Zhen,et al. An improved CV active contour model[J]. Photoelectric engineering,2008,35(12):112-116.
- [9]宋昱,吴一全,毕硕本.边缘修正CV模型的卫星遥感云图分割方法[J].光学学报,2014,34(9):30-37.SONG Yu,WU Yiquan,BI Shuoben. Satellite remote sensing cloud image segmentation method based on edge correction CV model[J]. Acta optica Sinica,2014,34(9):30-37.
- [10]陈宇飞,吴启迪,赵卫东,等.基于图像熵的快速ChanVese模型分割算法[J].同济大学学报(自然科学版),2011,39(5):738-744.CHEN Yufei,WU Qidi,ZHAO Weidong,et al. Fast ChanVese model segmentation algorithm based on image entropy[J]. Journal of Tongji University(natural science edition),2011,39(5):738-744.
- [11]龚勋,王国胤,李天瑞,等.基于混合能量活动轮廓模型的人脸分割方法[J].软件学报,2013,23(4):623-638.GONG Xun,WANG Guoyin,LI Tianrui,et al. Face segmentation method based on mixed energy active contour model[J].Journal of software,2013,23(4):623-638.
- [12] ZHANG K,SONG H,ZHANG L. Active contours driven by local image fitting energy[J]. Pattern recognition,2010,43(4):1199-1206.
- [13] LI C M,KAO C Y,GORE J C,et al. Implicit active contours driven by local binary fitting energy[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis:IEEE,2007:1-7.
- [14] LI Chunming,HUANG Rui,DING Zaohua,et al. A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI[J]. IEEE transactions on image processing,2011,20(7):2007-2016.
- [15] CHEN Yufei,LIANG Haiquan,YUE Xiaodong,et al. Active contour model with entropy-based constraint for image segmentation[C]//2016 SAI Computing Conference. London:IEEE,2016:255-263.
- [16]郝明,邓喀中,张华.基于遥感数据提取建筑物的主动轮廓改进模型[J].中国矿业大学学报,2012,41(5):833-838.HAO Ming,DENG Kazhong,ZHANG Hua. Active contour improvement model for building buildings based on remote sensing data[J]. Journal of China University of Mining&Technology,2012,41(5):833-838.
- [17] KASS M,WITKIN A,TERZOPOULOS D. Snakes:active contour models[J]. International journal of computer vision,1988,1(4):321-331.
- [18] LI C M,KAO C Y,GORE J C,et al. Minimization of regionscalable fitting energy for image segmentation[J]. IEEE transactions on image processing,2008,17(10):1940-1949.
- [19] SHE X X,HUANG F Z. Flame edge detection based on C-V active contour model[C]//2009 International Conference on Artificial Intelligence and Computational Intelligence. Shanghai:IEEE,2009:413-417.
- [20] DENG Y,LIU X,ZHENG Z,et al. A new active contour modeling method for processing-path extraction of flexible material[J]. International journal for light and electron optics,2016,127(13):5422-5429.