无需初始轮廓的图像分割模型

doi:10.11772/j.issn.1001-9081.2020071058

计算机应用 ›› 2021, Vol. 41 ›› Issue (4): 1179-1183.DOI: 10.11772/j.issn.1001-9081.2020071058

所属专题：多媒体计算与计算机仿真

• 多媒体计算与计算机仿真 • 上一篇下一篇

无需初始轮廓的图像分割模型

罗琴, 王艳

重庆师范大学数学科学学院, 重庆 401331

收稿日期:2020-07-21 修回日期:2020-10-08 发布日期:2020-11-12 出版日期:2021-04-10
通讯作者: 王艳
作者简介:罗琴（1995—），女，重庆人，硕士研究生，主要研究方向：图像处理的偏微分方程方法；王艳（1984—），女，山东青岛人，教授，博士，主要研究方向：图像处理的偏微分方程方法、医学影像处理与分析。
基金资助:
国家自然科学基金资助项目（11901071）；重庆市自然科学基金面上项目（cstc2019jcyj-msxmX0219）；中国博士后基金资助项目（2020M671685）；浙江省博士后科研项目（514000-X81902）。

Image segmentation model without initial contour

LUO Qin, WANG Yan

School of Mathematical Sciences, Chongqing Normal University, Chongqing 401331, China

Received:2020-07-21 Revised:2020-10-08 Online:2020-11-12 Published:2021-04-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (11901071), the Surface Program of Natural Science Foundation of Chongqing (cstc2019jcyj-msxmX0219), the China Postdoctoral Science Foundation (2020M671685), the Zhejiang Postdoctoral Research Project (514000-X81902).

摘要/Abstract

摘要： 为了增强对初始轮廓的鲁棒性并提高对灰度不均图像、噪声图像的分割效率，提出一种基于区域的活动轮廓模型。首先分别构造全局灰度拟合力与局部灰度拟合力，然后用线性组合获得模型的拟合项，并通过调整拟合力之间的权重提高模型对初始轮廓的鲁棒性，最后利用演化曲线的长度项保持曲线的光滑性。通过实验结果可以看出：与区域可变灰度拟合（RSF）模型和选择性局部或全局分割（SLGS）模型相比，所提模型的迭代步数分别减少了约57%和31%，分割时间分别减少了约62%和14%。所提模型在无需初始轮廓的情况下，不仅可以快速、准确地分割灰度不均图像和噪声图像，而且对医学图像和红外图像等一些实际应用图像也有很好的分割效果。

关键词: 图像分割, 水平集方法, 活动轮廓模型, 灰度不均图像, 噪声图像

Abstract: In order to enhance the robustness to initial contour as well as improve the segmentation efficiency for images with intensity inhomogeneity or noise, a region-based active contour model was proposed. First, a global intensity fitting force and a local intensity fitting force were designed separately. Then, the model's fitting term was obtained by the linear combination. And the weight between the two fitting forces were adjusted to improve the robustness of the model to the initial contour. Finally, the length term of evolution curve was employed to keep the smoothness of the curve. Experimental results show that compared with Region-Scalable Fitting(RSF) model and Selective Local or Global Segmentation(SLGS) model, the proposed model has the number of iterations reduced by about 57% and 31%, and the segmentation time reduced by about 62% and 14%. The proposed model can quickly and accurately segment noisy images and images with intensity inhomogeneity without initial contour. Besides, it has good segmentation effect on some practical images such as medical images and infrared images.

Key words: image segmentation, level set method, active contour model, image with intensity inhomogeneity, noisy image

中图分类号:

TP391.41

罗琴, 王艳. 无需初始轮廓的图像分割模型[J]. 计算机应用, 2021, 41(4): 1179-1183.

LUO Qin, WANG Yan. Image segmentation model without initial contour[J]. Journal of Computer Applications, 2021, 41(4): 1179-1183.

参考文献

[1] KHAN S,LEE D H,KHAN M A,et al. Efficient and improved edge detection via a hysteresis thresholding method[J]. Current Science,2020,118(6):954-960.
[2] 李社蕾, 黄梦醒. 改进几何活动轮廓模型的水下图像分割算法研究[J]. 小型微型计算机系统,2019,40(3):671-675.(LI S L, HUANG M X. Research of underwater image segmentation algorithm based on the improved geometric active contour models[J]. Journal of Chinese Computer Systems, 2019, 40(3):671-675.)
[3] HAN B, WU Y. Active contours driven by global and local weighted signed pressure force for image segmentation[J]. Pattern Recognition,2019,88:715-728.
[4] 王辉, 吴永武, 杜应琼. 一种图像分割模型的自适应参数选择方法[J]. 计算机应用与软件,2019,36(5):211-215.(WANG H, WU Y W,DU Y Q. An adaptive parameter selection method for image segmentation model[J]. Computer Applications and Software,2019,36(5):211-215.)
[5] DING K,XIAO L,WENG G. Active contours driven by regionscalable fitting and optimized Laplacian of Gaussian energy for image segmentation[J]. Signal Processing,2017,134:224-233.
[6] 吴漩, 王艳, 陈星. 无需初始轮廓的快速图像分割模型[J]. 计算机工程与应用,2019,55(11):167-171.(WU X,WANG Y, CHEN X. Fast image segmentation model without initial contour[J]. Computer Engineering and Applications,2019,55(11):167-171.)
[7] 刘金彦, 何传江, 吴永飞. 噪声鲁棒的水平集演化模型[J]. 计算机应用与软件,2016,33(4):173-176.(LIU J Y,HE C J,WU Y F. Level set evolution model robust to noise[J]. Computer Applications and Software,2016,33(4):173-176.)
[8] ZHOU S,WANG J,ZHANG S,et al. Active contour model based on local and global intensity information for medical image segmentation[J]. Neurocomputing,2016,186:107-118.
[9] FANG L,QIU T,ZHAO H,et al. A hybrid active contour model based on global and local information for medical image segmentation[J]. Multidimensional Systems and Signal Processing, 2019,30(2):689-703.
[10] 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.(LU Y Y, QIANG J R,WANG Z. Image segmentation based on active contours with local information[J]. Computer Engineering and Applications,2018,54(10):208-212.)
[11] CHAN T F,VESE L A. Active contours without edges[J]. IEEE Transactions on Image Processing,2001,10(2):266-277.
[12] LI C,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.
[13] 张洋, 唐克伦, 刘琰, 等. 一种改进的C-V主动轮廓模型[J]. 四川理工学院学报(自然科学版),2014,27(5):33-36.(ZHANG Y,TANG K L,LIU Y,et al. An improved active contour model based on C-V model[J]. Journal of Sichuan University of Science and Engineering (Natural Science Edition),2014,27(5):33-36.)
[14] 朱雷, 杨璟, 黄席樾. 局部C-V主动轮廓模型快速图像分割算法[J]. 重庆大学学报,2012,35(6):112-116.(ZHU L,YANG J, HUANG X Y. A fast image segmentation algorithm with local C-V active contour model[J]. Journal of Chongqing University,2012, 35(6):112-116.)
[15] ZHANG K,ZHANG L,SONG H,et al. Active contours with selective local or global segmentation:a new formulation and level set method[J]. Image and Vision Computing,2010,28(4):668-676.
[16] 刘瑞娟, 何传江, 原野. 融合局部图像信息的SLGS活动轮廓模型[J]. 计算机工程,2012,38(10):188-190.(LIU R J,HE C J,YUAN Y. SLGS active contour model fused with local image information[J]. Computer Engineering, 2012, 38(10):188-190.)
[17] 张栩源, 王艳. 用于灰度不均图像分割的自适应灰度拟合模型[J]. 计算机应用,2019,39(9):2719-2725.(ZHANG X Y, WANG Y. Adaptive intensity fitting model for segmentation of images with intensity inhomogeneity[J]. Journal of Computer Applications,2019,39(9):2719-2725.)
[18] 陈星, 王艳, 吴漩. 结合全局信息的局部图像灰度拟合模型[J]. 计算机应用,2018,38(12):3574-3579.(CHEN X,WANG Y, WU X. Local image intensity fitting model combining global image information[J]. Journal of Computer Applications,2018,38(12):3574-3579.)

无需初始轮廓的图像分割模型

Image segmentation model without initial contour

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	许立君, 黎辉, 刘祖阳, 陈侃松, 马为駽. 基于3D‑Ghost卷积神经网络的脑胶质瘤MRI图像分割算法3D‑GA‑Unet[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1294-1302.
[2]	顾聪, 段其强, 任思雨. 基于上下文感知网络的息肉分割算法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3617-3622.
[3]	梁军, 洪泽泓, 余松森. 基于改进粒子群优化算法和遗传变异的图像分割模型[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1743-1749.
[4]	傅励瑶, 尹梦晓, 杨锋. 基于Transformer的U型医学图像分割网络综述[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1584-1595.
[5]	兰冬雷, 王晓东, 姚宇, 王辛, 周继陶. 基于邻近切片注意力融合的直肠癌分割网络[J]. 《计算机应用》唯一官方网站, 2023, 43(12): 3918-3926.
[6]	窦猛, 陈哲彬, 王辛, 周继陶, 姚宇. 基于深度学习的多模态医学图像分割综述[J]. 《计算机应用》唯一官方网站, 2023, 43(11): 3385-3395.
[7]	林荐壮, 杨文忠, 谭思翔, 周乐鑫, 陈丹妮. 融合滤波增强和反转注意力网络用于息肉分割[J]. 《计算机应用》唯一官方网站, 2023, 43(1): 265-272.
[8]	徐光柱, 林文杰, 陈莎, 匡婉, 雷帮军, 周军. U-Net与自适应阈值脉冲耦合神经网络相结合的眼底血管分割方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 825-832.
[9]	李鸿, 邹俊颖, 谭茜成, 李贵洋. 面向医学图像分割的多注意力融合网络[J]. 《计算机应用》唯一官方网站, 2022, 42(12): 3891-3899.
[10]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[11]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[12]	黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827.
[13]	董阳, 潘海为, 崔倩娜, 边晓菲, 滕腾, 王邦菊. 面向多模态磁共振脑瘤图像的小样本分割方法[J]. 计算机应用, 2021, 41(4): 1049-1054.
[14]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[15]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.