改进边界指示函数的CV模型构建及应用

详细信息    查看全文 | 推荐本文 |

英文篇名：Construction and Application of CV Model for Improving Boundary Indicator Function 作者：夏小刚 ; 邓路娜 ; 鲁珍 英文作者：XIA Xiaogang;DENG Luna;LU Zhen;College of Science,Xi'an University of Science and Technology; 关键词：图像分割 ; 边界指示函数 ; CV模型 ; 水平集演化方程 ; 双阱势距离正则项 英文关键词：image segmentation;;boundary indication function;;CV model;;boundary indication function;;double-well potential distance regular term 中文刊名：JSGG 英文刊名：Computer Engineering and Applications 机构：西安科技大学理学院; 出版日期：2018-11-19 15:09 出版单位：计算机工程与应用 年：2019 期：v.55;No.933 基金：国家自然科学基金(No.71473194,No.71273206);; 陕西省科技厅自然科学基金(No.2013KJXX-40,No.2017JM1024);; 陕西省教育厅科学研究计划资助项目(No.16JK1500) 语种：中文; 页：JSGG201914026 页数：5 CN：14 分类号：183-187

摘要

无边缘活动轮廓CV模型对于边界模糊以及背景灰度分布不均匀的图像缺乏良好的分割效果。基于此,对该模型进行了如下改进。对边界指示函数进行修改,将改进后的边界指示函数融入CV模型的长度项中。引用双阱势的距离正则项来避免水平集重新初始化,从而得到了一个梯度与区域信息相结合的水平集演化方程,并应用变分法中的有限差分法对方程进行求解。对木材虫眼、活节和死节图像进行了数值仿真模拟,仿真结果表明该模型对背景分布不均匀的图像具有良好的分割效果。
        The CV model of edgeless active contours lacks a good segmentation effect for the images with blurred boundary and non-uniform background gray distribution. For this reason, the following improvements have been made to this model in this paper. Firstly, the boundary indicator function is modified and the improved boundary indicator function is integrated into the length of the CV model. Secondly, the distance regularization term of the double-well potential is introduced into the CV model to avoid re-initialization of the level set. Thus, a level set evolution equation combining gradient and region information is obtained, and the equation is solved using the finite difference method in variation method. Finally,the numerical simulation of wood bug, live knot and dead knot image is carried out. The simulation results show that the model has good segmentation effect for images with uneven background distribution.

引文

[1]Li Qianqian,Liu Qingyi,Li Lei,et al.An improved method based on CV and snake model for ultrasound image segmentation[C]//Seventh International Conference on Image and Graphics,2013:160-163.
    [2]鲁圆圆,强静仁,汪朝.基于区域信息主动轮廓模型的图像分割[J].计算机工程与应用,2018,54(10):208-212.
    [3]Osher S,Sethian J A.Fronts propagating with curvaturedependent speed:algorithms based on Hamilton-Jacobi formulations[J].J Computational Physics,1988,79(1):12-49.
    [4]Vese L,Chan T.A multiphase level set framework for imagesegmentation using the Mumford and Shah model[J].International Journal of Computer Vision,2002,50(1):271-293.
    [5]申铉京,于凯民,王开业,等.结合全局和局部灰度拟合活动轮廓模型的图像分割算法[J].吉林大学学报(工学版),2012,42(6):1532-1537.
    [6]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):22-29.
    [7]Xue W,Zhou Z,Zheng J,et al.Vessel segmentation using shape priors in level set framework[J].Journal of ComputerAided Design&Computer Graphics,2013,25(8):1213-1222.
    [8]Wu Y,Hao Y,Wu S,et al.Marine spill oil SAR image segmentation based on KFCM and improved CV model[J].Chinese Journal of Scientific Instrument,2012,33(12):2812-2818.
    [9]郑伟,张晶,杨虎.改进边界指示函数的水平集活动轮廓模型[J].激光技术,2016,40(1):126-130.
    [10]Zhang A,Fan W,Chen H.Multi-color object image segmentation based on improved CV model[J].Journal of Huazhong University of Science&Technology,2018,46(1):63-66.
    [11]Lankton S,Tannenbaum A.Localizing region-based active contours[J].IEEE Transactions on Image Processing,2008,17(11):2029.
    [12]Yu S,Wu Y,Dai Y.A new active contour remote sensing river image segmentation algorithm inspired from the cross entropy[J].Digital Signal Processing,2016,48:322-332.
    [13]韩斌,吴一全,宋昱.基于改进CV模型的煤矿井下早期火灾图像分割[J].煤炭学报,2017,42(6):1620-1627.
    [14]Amin A,Deriche M.Robust image segmentation based on convex active contours and the Chan Vese model[C]//Signal and Information Processing,2015:1044-1048.
    [15]Li C,Xu C,Gui C,et al.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254.
    [16]Zhao X,Zhou P,Xue M.Wavelet-based improved ChanVese model for image segmentation[C]//Proceedings of the SPIE,2016.光鴇光?鴇?鼇???????鼇?