一种基于局部符号差能量的非局部分割模型

J4 ›› 2016, Vol. 38 ›› Issue (05): 975-982.

一种基于局部符号差能量的非局部分割模型

闫沫1，王瑜2

（1.西安建筑科技大学机电工程学院,陕西西安 710055；2.西安航空学院机械学院,陕西西安 710077）

收稿日期:2015-04-17 修回日期:2015-06-26 出版日期:2016-05-25 发布日期:2016-05-25

A nonlocal segmentation model based
on local signed difference energy

YAN Mo1，WANG Yu2

（1.College of Mechanical and Electrical Engineering,Xi’an University of Architecture and Technology,Xi’an 710055;
2.School of Mechanical Engineering,Xi’an Aeronautical University,Xi’an 710077,China）

Received:2015-04-17 Revised:2015-06-26 Online:2016-05-25 Published:2016-05-25

摘要/Abstract

摘要：

针对灰度非均匀的图像，提出一种基于局部符号差能量的非局部图像分割模型。该模型包含基于局部符号差能量的数据驱动项和非局部全变分正则项，具有局部可分离性和全局一致性的特点。由于本文模型是凸的，因此在数值实现上可以采用splitBregman迭代算法，具有较快的运算速度。同经典的基于局部区域的主动轮廓分割模型相比，该方法具有以下优点：（1) 该模型受初始化的影响很小；（2) 采用splitBregman迭代算法，运算速度更快；（3) 能够对具有细密纹理和具有弱边缘目标的图像进行正确分割。实验结果表明，该模型对灰度非均匀图像能够进行较准确的分割，相比其他模型具有更好的鲁棒性。

关键词: 图像分割, 非局部全变分, 灰度非均匀, 局部符号差, splitBregman算法

Abstract:

We propose a nonlocal image segmentation model based on local signed difference (LSD) energy for images with intensity inhomogeneity. The model consists of a data driven term based on LSD energy and a nonlocal total variation regularization term, and possesses local separability and global consistency. Due to the convexity of the model, the splitBregman iteration algorithm can be used in the numerical implementation, thus having a fast speed. Compared with the classical local regionbased active contour models (ACMs), the proposed model has several advantages as follows: 1) it is less sensitive to the initialization; 2) it is more efficient by using the splitBregman iteration algorithm; 3) it can correctly segment images with fine textures and weak object boundaries. Experimental results show that the model can segment images with intensity inhomogeneity correctly and works more robust than other models.

Key words: image segmentation;nonlocal total variation;intensity inhomogeneity;LSD;splitBregman algorithm

闫沫1，王瑜2. 一种基于局部符号差能量的非局部分割模型[J]. J4, 2016, 38(05): 975-982.

YAN Mo1，WANG Yu2. A nonlocal segmentation model based
on local signed difference energy[J]. J4, 2016, 38(05): 975-982.

参考文献［10］

［1］	Caselles V, Kimmel R, Sapiro G. Geodesic active contours ［J］.International Journal of Computer Vision,1997,22(1):6179.
［2］	Zhang K,Zhang L,Song H,et al.Reinitialization free level set evolution via reaction diffusion ［J］.IEEE Transactions on Image Processing,2013,22(1):258271.
［3］	Chan T,Vese L.Active contours without edges ［J］.IEEE Transactions on Image Processing,2001,10(2):266277.
［4］	Wang L,Yu Z,Pan C.A unified level set framework utilizing parameter priors for medical image segmentation ［J］.Science China Information Sciences,2013,56(11):114.
［5］	Li C,Kao C,Gore J,et al.Minimization of regionscalable fitting energy for image segmentation ［J］.IEEE Transactions on Image Processing,2008,17(10):19401949.
［6］	Wang L,He L,Mishra A,et al.Active contours driven by local Gaussian distribution fitting energy ［J］.Singnal Processing,2009,89(12):24352447.
［7］	Zhang K,Song H,Zhang L.Active contours driven by local image fitting energy ［J］.Pattern Recognition,2010,43(4):11991206.
［8］	Kong Dingke,Wang Guozhao.Edgepreserving local fitting model for image segmentation ［J］.Journal of Zhejiang University (Engineering Science),2010,44(12):22362240.(in Chinese)
［9］	Liu Jianlei,Feng Dazheng.Nonhomogenous image segmentation with global optimization ［J］.Journal of Xidian University,2011,38(2):6671.(in Chinese)
［10］	Xue Weiqin,Zhou Zhiyong,Zhang Tao,et al.Vessel segmentation under nonuniform illumination:A level set approach ［J］.Journal of Software,2012,23(9):24892499.(in Chinese)
［11］	Wang L,Wu H,Pan C.Regionbased image segmentation with local signed difference energy ［J］.Pattern Recognition Letters,2013,34:637645.
［12］	Chan T F, Esedoglu S, Nikolova M.Algorithms for finding global minimizers of image segmentation and denoising models［J］.SIAM Journal Applied Mathematics,2006,66(5):16321648.
［13］	Goldstein T,Bresson X,Osher S.Geometric applications of the split Bregman method Segmentation and surface reconstruction ［J］.Journal Science Computing, 2010,45(1):272293.
［14］	Zhang X,Burger M,Bresson X,et al.Bregmanized nonlocal regularization for deconvolution and sparse reconstruction ［J］.SIAM Journal on Imaging Science,2010,3(3):253276.
［15］	Zosso D,Tran G,Osher S J.Nonlocal Retinex—a unifying framework and beyond［J］.SIAM Journal on Image Science,2015,8(2):787826.
［16］	Mumford D,Shah J.Optimal approximations by piecewise smooth functions and associated variational problems ［J］.Communications on Pure Applied Mathematics,1989,42(5):577685.
	附中文参考文献：
［8］	孔丁科,汪国昭.用于图像分割的边界保持局部拟合模型［J］.浙江大学学报（工学版）,2010,44(12):22362240.
［9］	刘建磊,冯大政.一种全局最优的非匀质图像分割算法［J］.西安电子科技大学学报,2011,38(2):6671.
［10］	薛维琴,周志勇,张涛,等.灰度不均的弱边缘血管影像的水平集分割方法［J］.软件学报,2012,23(9):24892499.

[1]	吴从中, 董浩, 方静. 基于注意力机制的自适应滤波遥感图像分割网络[J]. 计算机工程与科学, 2022, 44(11): 2010-2018.
[2]	仇静博, 燕雪峰, 汪俊, 郭延文, 魏明强, . 基于全卷积神经网络的单幅隧道图像裂纹提取算法[J]. 计算机工程与科学, 2022, 44(05): 845-854.
[3]	曾增峰, 环宇翔, 邹卓, 郑立荣. 多尺度深度监督的高度近视萎缩病变分割方法[J]. 计算机工程与科学, 2021, 43(07): 1264-1272.
[4]	蒋芸, 高静, 王发林. SAG-Net：用于联合视盘和视杯分割的新型跳过注意力指导网络[J]. 计算机工程与科学, 2021, 43(07): 1273-1282.
[5]	张俊鹏, 刘辉, 李清荣. 基于FCN-LSTM的工业烟尘图像分割[J]. 计算机工程与科学, 2021, 43(05): 906-916.
[6]	陈爱莲, 丁正龙, 詹曙. 基于对抗学习和多尺度特征融合的前列腺MR图像分割[J]. 计算机工程与科学, 2021, 43(04): 697-703.
[7]	朱倩倩, 车文刚, 苗晗. 数字化藏文古籍中多样性字体的实现方法研究[J]. 计算机工程与科学, 2020, 42(11): 2073-2079.
[8]	赵仁和，王军锋. 自适应尺度的局部强度聚类图像分割模型[J]. 计算机工程与科学, 2020, 42(06): 1043-1048.
[9]	徐秋平. 基于人机交互式图割的目标快速提取[J]. 计算机工程与科学, 2020, 42(02): 299-306.
[10]	王卫民1,符首夫1,顾榕蓉1,王东升1,何林容2,关文斌3. 基于卷积神经网络的虫情图像分割和计数方法[J]. 计算机工程与科学, 2020, 42(01): 110-116.
[11]	任佳1,2，张胜男1，董超2，赵敏钧1. 基于改进模糊C均值的海面目标图像分割算法[J]. 计算机工程与科学, 2019, 41(05): 858-864.
[12]	吴尚智1，佘志用2，张霞1，赵慧琴3. 利用变精度粗糙熵的图像分割算法[J]. 计算机工程与科学, 2018, 40(10): 1837-1843.
[13]	易三莉，张桂芳，贺建峰，李思洁. 基于最大类间方差的最大熵图像分割[J]. 计算机工程与科学, 2018, 40(10): 1874-1881.
[14]	刘汉强，张青. 区间模糊谱聚类图像分割方法[J]. 计算机工程与科学, 2018, 40(09): 1611-1616.
[15]	谭志国1，2,欧建平1,张军1,沈先耿2. 多特征组合的深度图像分割算法[J]. 计算机工程与科学, 2018, 40(08): 1429-1434.