[1]ZHENG Jiaming,CHEN Zhaojiong.Interactive Graph-Cut for image segmentation using local color models[J].CAAI Transactions on Intelligent Systems,2011,6(4):318-323.
Copy

Interactive Graph-Cut for image segmentation using local color models

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 6 Number of periods: 2011 4 Page number: 318-323 Column: 学术论文—人工智能基础 Public date: 2011-08-25
Title:
Interactive Graph-Cut for image segmentation using local color models
Author(s):
ZHENG Jiaming;  CHEN Zhaojiong
College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350108, China
Keywords:
Graph-Cut;  interactive image segmentation;  MeanShift;  real time interactivity
CLC:
TP391
DOI:
-
Abstract:
Most interactive segmentation algorithms based on GraphCut do not usually lend themselves to real time applications with accurate segmentation. In this paper, an improved algorithm using local color models was proposed to deal with the problem. Using MeanShift technology, the proposed algorithm built an interactive image segmentation framework based on local color models. A GraphCut algorithm was then applied to the presegmented regions instead of image pixels. The presegmented regions preserve the image structure, which improves the estimation accuracy of distribution based on local color models and dramatically reduces the computational complexity. Experimental results show that the proposed algorithm has good real time interactivity with accurate segmentation. 
References:
［1］KASS M, WITKIN A, TERZOLPOULOS D. Snakes: active contour models［J］. International Journal of Computer Vision, 1988, 1(4): 321331. 
［2］YUNRI Y, JOLLY B M P. Interactive graph cuts for optimal boundary and region segmentation of objects in ND images［C］//Proceedings of International Conference on Computer Vision. Vancouver, Canada, 2001, 1: 105112.
［3］ROTHER C, KOLMOGOROV V, BLAKE A. Grabcutinteractive foreground extraction using iterated graph cuts ［J］. ACM Transactions on Graphics, 2004, 23(3): 309314.
［4］LI Yin, SUN Jian, TANG Chikeung, et al. Lazy snapping［C］//Computer Graphics Proceedings, Annual Conference Series(ACM SIGGRAPH). Los Angeles, USA, 2004： 303308.
［5］VICENTE A， KOLMOGOROV V, ROTHER C. Graph cut based image segmentation with connectivity priors［C］//Proceeding of IEEE International Conference on CVPR.［S.l.］, 2008： 18.
［6］刘陈，李凤霞，张艳. 图割与泛形信息结合［J］.计算机辅助设计与图形学学报, 2009, 21(12): 17531760.
LIU Chen, LI Fengxia, ZHANG Yan. An interactive object cutout algorithm based on graphcut and generalized shape prior［J］. Journal of Computeraided Design & Computer Graphics, 2009, 21(12): 17531760. 
［7］COMANICIU D, MEER P. Mean shift: a robust approach toward feature space analysis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603619. 
［8］RHEMANN C, ROTHER C, WANG J. A perceptually motivated online benchmark for image matting［C］// Proceedings of IEEE International Conference on CVPR. 2009： 18261833.
［9］YUNRI Y, BOYKOV, KOLMOGOROV V. An experimental comparison of mincut/maxflow algorithms for energy minimization in vision［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 11241137.
［10］ KOLMOGOROV V, ZABIH R. What energy functions can be minimized via graph cuts［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 147159.
Similar References:

Memo

-

Last Update: 2011-09-30

Copyright © CAAI Transactions on Intelligent Systems