全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于超像素的多主体图像交互分割

DOI: 10.11834/jig.20150605

Keywords: 图像分割,多主体分割,超像素,图割法,网络流

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的为解决多主体图像的交互分割问题,在保证分割效果的前提上,提高分割的效率,达到实时交互修改分割结果的目的,提出基于超像素的图像多主体交互分割算法.方法基于图像的超像素构造一个多层流网络,利用用户交互绘制的简单笔画给出多主体分割的指导信息.流网络的边权值保证利用图割算法将图像分割成多个部分后,每个部分代表图像的一个主体.允许用户交互给出标记,实时修改分割结果,直到得到满意的多主体分割.结果通过实验显示,本文方法能得到的满意多主体分割结果,而且时间效率较高.对分辨率为449×275的图像,算法能在1s内给出结果,满足实时修改的要求.结论基于超像素建立的图规模较小,能大大减少图割算法的运行时间,达到用户实时交互添加新笔画信息,交互地修正分割结果的目的.利用超像素的边界信息,用户只需输入比较简单的笔画信息,分割算法就能得到正确的多主体分割结果.

References

[1]  Wang L B, Guo Y W, Xia T C, et al. Example-driven semi-automatic image collection segmentation [J]. Journal of Computer Aided Design and Computer Graphics, 2013, 25(6): 794-801. [汪粼波,郭延文,夏天辰,等.样本驱动的半自动图像集前背景分割[J]. 计算机辅助设计与图形学学报,2013,25(6):794-801.]
[2]  Wu H, Xu D. Color preserved image compositing [J]. Chinese Journal of Software, 2012,23:94-104. [吴昊,徐丹.一种保持颜色的图像合成算法[J]. 软件学报,2012,23:94-104.]
[3]  Levinshtein A, Stere A, Kutulakos K N, et al. TurboPixels: fast superpixels using geometric flows [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,30(12): 2290-2297.
[4]  Radhakrishna A, Appu S, Kelvin S, et al. SLIC Superpixels [R]. Lausanne, Switzerland: Swiss Federal Institute of Technology in Lausanne, 2010.
[5]  Radhakrishna A, Appu S, Kelvin S, et al. SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
[6]  Wang P, Zeng G, Gan R, et al. Structure sensitive superpixels via geodesic distance [J].International Journal of Computer Vision, 2013, 103(1): 1-21.
[7]  Sethian J A. A fast marching level set method for monotonically advancing fronts [J]. Proc. Natl. Acad. Sci., USA, 1996, 93(4): 1591-1595.
[8]  Edelsbrunner H, Seidel R. Voronoi diagrams and arrangements [J]. Discrete & Computational Geometry, 1986, 1(1): 25-44.
[9]  Ning J F, Zhang L, Zhang D, et al. Interactive image segmentation by maximal similarity based region merging [J]. Pattern Recognition, 2010, 43(2): 445-456.
[10]  Li Y, Sun J, Tang C K, et al. Lazy snapping [J]. ACM Transactions on Graphics, 2004,23(3): 303-308.
[11]  Rother C, Kolmogorov V, Blake A. Grab Cut Interactive Foreground Extraction using Iterated Graph Cuts [J]. ACM Transactions on Graphics, 2004, 23(3): 309-314.
[12]  Xu X L, Lu Z M, Zhang G S, et al. Color image segmentation based on improved affinity propagation clustering [J]. Journal of Computer Aided Design and Computer Graphics, 2012, 24(4): 514-519. [许晓丽,卢志茂,张格森,等. 改进近邻传播聚类的彩色图像分割[J].计算机辅助设计与图形学学报,2012,24(4):514-519.]
[13]  Tao W B, Chang F, Liu L M, et al. Interactively multiphase image segmentation based on variational formulation and Graph Cuts [J]. Pattern Recognition, 2010, 43(10): 3208-3218.
[14]  Grady L. Random walks for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(12): 2290-2297.
[15]  Boykov Y, Kolmogorov V. An experimentalcomparison 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.
[16]  Yan L, Zhou Z, Wu W. Scene parsing based on a two-level conditional random field [J]. Chinese Journal of Computers,2013, 9:1898-1907. [艳丽,周忠,吴威. 一种双层条件随机场的场景解析方法[J].计算机学报,2013,9:1898-1907.]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133