Lazy snapping

被引:768
作者
Li, Y [1 ]
Sun, J
Tang, CK
Shum, IY
机构
[1] Hong Kong Univ Sci & Technol, Hong Kong, Hong Kong, Peoples R China
[2] Microsoft Res Asia, Beijing, Peoples R China
来源
ACM TRANSACTIONS ON GRAPHICS | 2004年 / 23卷 / 03期
关键词
user interface; image cutout; interactive image segmentation; graph cut;
D O I
10.1145/1015706.1015719
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In this paper, we present Lazy Snapping, an interactive image cutout tool. Lazy Snapping separates coarse and fine scale processing, making object specification and detailed adjustment easy. Moreover, Lazy Snapping provides instant visual feedback, snapping the cutout contour to the true object boundary efficiently despite the presence of ambiguous or low contrast edges. Instant feedback is made possible by a novel image segmentation algorithm which combines graph cut with pre-computed over-segmentation. A set of intuitive user interface (UI) tools is designed and implemented to provide flexible control and editing for the users. Usability studies indicate that Lazy Snapping provides a better user experience and produces better segmentation results than the state-of-the-art interactive image cutout tool, Magnetic Lasso in Adobe Photoshop.
引用
收藏
页码:303 / 308
页数:6
相关论文
共 19 条
[1]  
AGARWALA A, 2004, P ACM SIGGRAPH 2004
[2]  
BARRETT WA, 2002, P ACM SIGGRAPH 2002
[3]  
Boykov Y., 2001, P ICCV 2001
[4]  
BOYKOV Y, 2001, ENERGY MINIMIZATION
[5]  
CHUANG Y, 2001, P CVPR 2001
[6]  
Duda R. O., 2000, PATTERN CLASSIFICATI
[7]  
FAILS J, 2003, P C HUM FACT COMP SY
[8]  
FALCAO AX, 2000, IC0012
[9]   STOCHASTIC RELAXATION, GIBBS DISTRIBUTIONS, AND THE BAYESIAN RESTORATION OF IMAGES [J].
GEMAN, S ;
GEMAN, D .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) :721-741
[10]  
GLEICHER M, 1995, P ACM SIGGRAPH 95