[1]曾宪华,易荣辉,何姗姗.流形排序的交互式图像分割[J].智能系统学报编辑部,2016,11(1):117-123.[doi:10.11992/tis.201505037]
 ZENG Xianhua,YI Ronghui,HE Shanshan.Interactive image segmentation based on manifold ranking[J].CAAI Transactions on Intelligent Systems,2016,11(1):117-123.[doi:10.11992/tis.201505037]
点击复制

流形排序的交互式图像分割(/HTML)
分享到:

《智能系统学报》编辑部[ISSN:1673-4785/CN:23-1538/TP]

卷:
第11卷
期数:
2016年1期
页码:
117-123
栏目:
出版日期:
2016-02-25

文章信息/Info

Title:
Interactive image segmentation based on manifold ranking
作者:
曾宪华12 易荣辉12 何姗姗12
1. 重庆邮电大学计算机科学与技术学院, 重庆 400065;
2. 重庆邮电大学计算智能重庆市重点实验室, 重庆 400065
Author(s):
ZENG Xianhua12 YI Ronghui12 HE Shanshan12
1. College of Computer Science and Technology, Chongqing University of Posts and Telecommunication, Chongqing 400065, China;
2. Chongqing Key Laboratory of Computational Intelligence, Chongqing University of Posts and Telecommunication, Chongqing 400065, China
关键词:
流形排序交互式图像分割显著目标目标检测显著图背景标记目标标记
Keywords:
manifold rankinginteractive image segmentationsaliency objectobject detectionsaliency mapbackground labelobject label
分类号:
TP319.4
DOI:
10.11992/tis.201505037
摘要:
针对显著目标检测难以获得有效的目标整体检测导致目标分割困难的问题,采用一种在初始显著图的指导下添加有效交互信息的方式来获得目标的准确分割。该方法利用边界先验对超像素进行流形排序获得初始显著图,参照显著图对不显著的目标部分添加目标标记,显著背景部分添加背景标记,利用标记信息对超像素重新进行流形排序,将获得的显著图与初始显著图融合,对融合后的显著图采用自适应阈值法来获得目标的分割。在BSD图像数据库中的实验得到的平均正确分割率(TPR)和平均错误分割率(FPR)优于经典的最大相似合并图像分割算法(MSRM),表明了该算法能有效分割出正确的目标。
Abstract:
The unsatisfactory results of salient object detection have made object segmentation difficult. In this study, we obtain accurate object segmentation by combining effective interactive information under the guidance of an initial saliency map. This method obtains the original saliency map using priori boundaries of the manifold ranking of the superpixels, and based on the obtained saliency map, marks the object labels of the non-salient object parts and the background labels of the salient background parts. Next, the superpixels for generating the new saliency map are re-sorted by manifold ranking with label information, and the newly obtained and original saliency maps are merged. Finally, object segmentation is achieved by adopting the adaptive threshold method for the merged saliency map. Image segmentation experiments with images from the Berkeley segmentation dataset (BSD) image database demonstrate that the proposed method can correctly segment objects from images and that the true positive rate (TPR) and the false positive rate (FPR) results are better than those achieved using the classical maximal similarity-based region merging (MSRM) image segmentation algorithm.

参考文献/References:

[1] MORTENSEN E, MORSE B, BARRETT W, et al. Adaptive boundary detection using ‘live-wire’ two-dimensional dynamic programming[C]//Proceedings of Computers in Cardiology. Durham, North Carolina, UK, 1992:635-638.
[2] HE Huiguang, TIAN Jie, LIN Yao, et al. A new interactive segmentation scheme based on fuzzy affinity and live-wire[C]//Proceedings of the 2nd International Conference on Fuzzy Systems and Knowledge Discovery. Changsha, China, 2005:436-443.
[3] KASS M, WITKIN A, TERZOPOULOS D. Snakes:Active contour models[J]. International journal of computer vision, 1988, 1(4):321-331.
[4] GRADY L, FUNKA-Lea G. Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials[C]//Proceedings of the Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis. Prague, Czech Republic, 2004:230-245.
[5] GRADY L, SINOP A K. Fast approximate random walker segmentation using eigenvector precomputation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA, 2008:1-8.
[6] BOYKOV Y Y, JOLLY M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]//Proceedings of the 8th IEEE International Conference on Computer Vision. Vancouver, BC, Canada, 2001, 1:105-112.
[7] LI Yin, SUN Jian, TANG C K, et al. Lazy snapping[J]. ACM transactions on graphics (TOG), 2004, 23(3):303-308.
[8] NING Jifeng, ZHANG Lei, ZHANG D, et al. Interactive image segmentation by maximal similarity based region merging[J]. Pattern recognition, 2010, 43(2):445-456.
[9] MA Yufei, ZHANG Hongjiang. Contrast-based image attention analysis by using fuzzy growing[C]//Proceedings of the 11th ACM International Conference on Multimedia. New York, USA, 2003:374-381.
[10] GOPALAKRISHNAN V, HU Yiqun, RAJAN D. Salient region detection by modeling distributions of color and orientation[J]. IEEE transactions on multimedia, 2009, 11(5):892-905.
[11] WEI Yichen, WEN Fang, ZHU Wangjiang, et al. Geodesic saliency using background priors[C]//Proceedings of the 12th European Conference on Computer Vision. Florence, Italy, 2012:29-42.
[12] YANG Chuan, ZHANG Lihe, LU Huchuan, et al. Saliency detection via graph-based manifold ranking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, OR, USA, 2013:3166-3173.
[13] ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels, Technical Report on 149300[R]. EPFL, Lausanne, Switzerland, 2010.
[14] ZHOU Dengyong, WESTON J, GRETTON A, et al. Ranking on data manifolds[J]. Advances in neural information processing systems, 2004, 16:169-176.
[15] ZHOU D, BOUSQUET O, LAL T N, et al. Learning with local and global consistency[J]. Advances in neural Information processing systems, 2004, 16:321-328.
[16] ARBELAEZ P, FOWLKES C, MARTIN D. A database of human segment natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Poceeding of the 18th International Conference on Computer Vision,Vancouver,B.C., Canada, 2001,416-423.

相似文献/References:

[1]郑加明,陈昭炯.局部颜色模型的交互式Graph-Cut分割算法[J].智能系统学报编辑部,2011,6(04):318.
 ZHENG Jiaming,CHEN Zhaojiong.Interactive Graph-Cut for image segmentation using local color models[J].CAAI Transactions on Intelligent Systems,2011,6(1):318.
[2]练浩,曾宪华,李淑芳.有监督全局流形排序的图像检索算法[J].智能系统学报编辑部,2014,9(01):92.[doi:10.3969/j.issn.1673-4785.201303021]
 LIAN Hao,ZENG Xianhua,LI Shufang.Supervised global manifold ranking based image retrieval algorithm[J].CAAI Transactions on Intelligent Systems,2014,9(1):92.[doi:10.3969/j.issn.1673-4785.201303021]

备注/Memo

备注/Memo:
收稿日期:2015-05-19;改回日期:。
基金项目:国家自然科学基金重点资助项目(U1401252);国家自然科学基金资助项目(61075019,61379114);重庆市基础与前沿研究计划资助项目(cstc2015jcyjA40036).
作者简介:曾宪华,男,1973年生,副教授,博士,中国计算机学会会员,主要研究方向为流形学习、计算机视觉等。主持国家自然科学基金、重庆自然科学基金等省级以上项目3项。发表学术论文30余篇;易荣辉,男,1988年生,硕士研究生,主要研究方向为流形学习、图像分割等;何姗姗,女,1992年生,硕士研究生,主要研究方向为流形学习、图像分割等。
通讯作者:曾宪华.E-mail:xianhuazeng2005@163.com.
更新日期/Last Update: 1900-01-01