基于交互式图论的目标边缘检测算法

J4 ›› 2014, Vol. 36 ›› Issue (08): 1571-1575.

基于交互式图论的目标边缘检测算法

林选伟，吴谨

（武汉科技大学信息科学与工程学院，湖北武汉 430081）

收稿日期:2012-12-04 修回日期:2013-04-03 出版日期:2014-08-25 发布日期:2014-08-25
基金资助:
国家自然科学基金资助项目（60974012,61171160）；湖北省教育厅科研计划项目（Q20131110）；高等学校博士学科点专项科研基金（20124219120002）；武汉科技大学青年科技骨干培养计划项目（2013xz010）；国家级大学生创新创业训练计划项目（201210488062）

A novel target edge detection algorithm based on interactive graph theory

LIN Xuanwei,WU Jin

(College of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,China)

Received:2012-12-04 Revised:2013-04-03 Online:2014-08-25 Published:2014-08-25

摘要/Abstract

摘要：

针对传统边缘检测算法无法准确提取目标及其边缘的问题，基于交互式图论的最大流/最小割理论提出了一种新的边缘检测算法，设计了一种新的代价函数OE_COST目标边缘代价函数；通过建立图割模型，能够在分割出目标的同时提取出目标边缘。算法通过交互式选择背景及目标像素集合作为硬性约束，通过图像特征（如灰度级、空间信息等）建立代价函数作为软性约束，同时施加软硬约束达到提取目标边缘的目的。实验结果表明，本算法可以准确提取出目标及其边缘轮廓。

关键词: 边缘检测, 交互式, 图论, 最大流/最小割, 代价函数

Abstract:

As the traditional algorithm for edge detection cannot extract the targets and edges accurately, based on the maxflow/min-cut theory of interactive graph theory, a novel edge detection method is proposed and a new cost-function, named Objects Edge Cost (OE_COST), is designed. The proposed algorithm establishes the graph cut mode to cut the objects and get their edges. The algorithm can extract the edges of targets through combining the hard constraints and soft constraints. The hard constraints can be got by selecting background seeds and object seeds interactively, while the soft constraints are based on the properties of images such as gray levels and space information. Experimental results show that the proposed algorithm can obtain the objects and edges exactly.

Key words: edge detection;interactive;graph theory;max-flow/min-cut;cost-functions

林选伟，吴谨. 基于交互式图论的目标边缘检测算法[J]. J4, 2014, 36(08): 1571-1575.

LIN Xuanwei,WU Jin. A novel target edge detection algorithm based on interactive graph theory [J]. J4, 2014, 36(08): 1571-1575.

参考文献［1］

［1］	Wang Chengliang, Lan Libin.Imge interpolation algorithm based on edge detection of fractional differential［J］.Journal of Beijing Institute of Technology, 2011,32(9):10861088.(in Chinese)
［2］	Saini K, Dewal M L, Rohit M. A fast regionbased active contour model for boundary detection of echocardiographic images［J］.J Digit Imaging, 2012, 25(2):271278.
［3］	Laligant O,Truchetet F. A nonlinear derivative scheme applied to edge detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,32(2):242256.
［4］	Park H, Mitsumine H, Fujii M. Adaptive edge detection for robust modelbased camera tracking［J］. IEEE Transactions on Consumer Electronics,2011,57(4):14651470.
［5］	Boykov Y Y，Jolly M P.Interactive graph cuts for optimal boundary & region segmentation of objects in ND images［C］∥Proc of International Conference on Computer Vision,2001:105110.
［6］	Li Shifeng,Lu Huchuan.Arbitrary body segmentation with a novel graph cutsbased algorithm［J］. IEEE Signal Processing Letters, 2011,18(12):753756.
［7］	Harish Kumar J R, Chaturvedi A. Edge detection of femur boneA comparative study［C］∥Proc of 2010 International Conference on Signal and Image Processing,2010:281284．
［8］	Tao Wenbing, Jin Hai, Zhang Yimin, et al. Image thresholding using graph cuts［J］. IEEE Transactions on Systems, Man, and CyberneticsPart A:Systems and Humans,2008,38(5):11811194.
［9］	Alonso M T, LópezMartínez C, Mallorquí J J, et al. Edge enhancement algorithm based on the wavelet transform for automatic edge detection in SAR images［J］. IEEE Transactions on Geoscience and Remote Sensing, 2011,49(1):222234.
［10］	Cormen T H, Leiserson C E, Ronald L, et al. Introduction to algorithms［M］.Beijing:China Machine Press, 2006:651660.
	附中文参考文献：
［1］	汪成亮,兰利彬. 采用分数阶微分边缘检测的图像插值［J］. 北京理工大学学报，2011,32(9):10861088．

[1]	王晓琦, 赵宣植, 刘增力, . 基于多尺度小波和Tsallis熵的水下图像边缘检测[J]. 计算机工程与科学, 2023, 45(07): 1245-1252.
[2]	李忠瑞, 崔宾阁, 杨光, 张昊卿. 基于深度学习的海岸线边缘检测网络模型[J]. 计算机工程与科学, 2022, 44(12): 2220-2229.
[3]	徐琨, 赵启雯, 徐源, 柳有权. 基于边缘检测的快速纸张检测方法[J]. 计算机工程与科学, 2022, 44(10): 1795-1803.
[4]	李凯, 张永生, 童晓冲, 李峰. 基于各向异性和边缘强度修正因子的边缘检测算法[J]. 计算机工程与科学, 2021, 43(07): 1256-1263.
[5]	赵月, 王来花, 齐苏敏, 王伟胜, 刘晨. 基于全局和局部特征的无参考夜间图像质量评价[J]. 计算机工程与科学, 2021, 43(07): 1283-1290.
[6]	蔡晨1,2，罗可1,2 . 融合BTM和图论的微博检索模型[J]. 计算机工程与科学, 2019, 41(08): 1512-1518.
[7]	周洲，黄茜，胡志辉. 基于显著性判别的缺陷检测方法[J]. 计算机工程与科学, 2018, 40(12): 2219-2223.
[8]	郭伟，董宏亮，赵德冀. 基于截断奇异值低秩矩阵恢复的Canny边缘检测算法[J]. 计算机工程与科学, 2018, 40(09): 1670-1678.
[9]	郭伟，董宏亮，石尚. 基于多尺度自适应扩散方程的边缘检测方法[J]. 计算机工程与科学, 2018, 40(05): 863-871.
[10]	陈诗军1，王慧强2，陈大伟1，刘秀兵2,胡海婧2. 基于改进禁忌搜索的基站布局优化算法[J]. 计算机工程与科学, 2018, 40(02): 341-347.
[11]	林雪松1，杨万清1，夏元斗1，程松2. 基于认知的智能电网家域接入控制网络非合作博弈功率控制算法比较研究[J]. 计算机工程与科学, 2016, 38(12): 2529-2535.
[12]	周东傲，林嘉宇. 视频图像文字检测综述[J]. J4, 2015, 37(04): 760-764.
[13]	罗晓霞，王莉青，薛弘晔. 基于小波变换和曲波变换的图像边缘检测新算法[J]. J4, 2015, 37(01): 157-161.
[14]	王昭顺1，徐柏权2. 一种基于蓝牙的交互式系统设计与实现[J]. J4, 2014, 36(08): 1500-1504.
[15]	杨雪1，李志华1,2. 一种新的渣土车车轮带泥检测方法[J]. J4, 2014, 36(04): 751-757.