计算机科学 ›› 2016, Vol. 43 ›› Issue (11): 309-312.doi: 10.11896/j.issn.1002-137X.2016.11.060

• 图形图像与模式识别 • 上一篇    下一篇

形状模板约束的图像协同分割

潘翔,余慧斌,郑河荣,刘志   

  1. 浙江工业大学计算机科学与技术学院 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受省自然科学基金项目(LY15F020024,LY16F020033),浙江省文物局(2014014)资助

Image Co-segmentation by Constraints of Shape

PAN Xiang, YU Hui-bin, ZHENG He-rong and LIU Zhi   

  • Online:2018-12-01 Published:2018-12-01

摘要: 已有的协同分割方法没有考虑到同一类图像所具有的目标形状相似性,从而使得分割结果不一致。提出了形状模板约束的图像交互协同分割算法,通过少量用户交互提高协同分割质量。该算法首先定义形状模板;然后通过形状上下文实现分割结果传递,自动形成图像分割所需的前景和背景掩码;最后采用最小割理论进行分割边界优化。实验结果表明,与已有的协同分割算法相比,该算法能在简单用户交互下明显提高分割质量,使分割结果更具有语义性。

关键词: 图像协同分割,形状模板,形状上下文,图割

Abstract: Existing image co-segmentation method fails to consider the similarity of shape between images,so that the segmentation results are inconsistent.We introduced a method of interactive image co-segmentation by the constraints of shape.First,the method preprocess an input image and finds the template of shape.Secondly,shape context matching algorithm is used to produce foreground and background mask for graph cut.Finally,minimum cut theory is used to optimize segmentation boundary.The experimental results show that compared with existing image co-segmentation method,this algorithm can significantly improve the quality of segmentation and make the segmentation results more semantical.

Key words: Image co-segmentation,Shape template,Shape context,Graph cut

[1] Ling kai,Wu Jun-hui,Xu Li-hong.A Survey on Color ImageSegmentation Techniques[J].Journal of Image and Graphics,2005,10(1):1-10(in Chinese) 林开颜,吴军辉,徐立鸿.彩色图像分割方法综述[J].中国图象图形学报,2005,10(1):1-10
[2] Rother C,Kolmogorov V,Blake A.“GrabCut ”--interactive foreground extraction using iterated graph cuts[J].Acm Transactions on Graphics,2004,23(3):309-314
[3] Ning J,Zhang L,Zhang D,et al.Interactive image segmentation by maximal similarity based region merging[J].Pattern Recognition,2010,43(2):445-456
[4] Liu Song-tao,Yin Fu-liang.The basic principle and its new advances of image segmentation methods based on graph cuts[J].Acta Automatica Sinica,2012,38(6):911-922(in Chinese) 刘松涛,殷福亮.基于图割的图像分割方法及其新进展[J].自动化学报,2012,38(6):911-922
[5] Rother C,Minka T,Blake A,et al.Cosegmentation of ImagePairs by Histogram Matching-Incorporating a Global Constraint into MRFs[C]∥2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.IEEE,2006:993-1000
[6] Hochbaum D S,Singh V.An efficient algorithm for Co-segmentation[C]∥IEEE International Conference on Computer Vision.2009:269-276
[7] Bach F,Ponce J.Discriminative clustering for image co-segmentation[C]∥IEEE Conference on Computer Vision & Pattern Recognition.2010:1943-1950
[8] Peng J,Singh V,Mukherjee L.Scale invariant cosegmentationfor image groups[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2011:1881-1888
[9] Collins M D,Xu J,Grady L,et al.Random walks based multi-image segmentation:Quasiconvexity results and GPU-based solutions[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2012:1656-1663
[10] Meng F,Li H,Liu G,et al.Image Cosegmentation by Incorpora-ting Color Reward Strategy and Active Contour Model[J].IEEE Transactions on Cybernetics,2012,43(2):725-737
[11] Batra D,Kowdle A,Parikh D,et al.iCoseg:Interactive co-segmentation with intelligent scribble guidance[C]∥2013 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2010:3169-3176
[12] Gulshan V,Rother C,Criminisi A,et al.Geodesic Star Convexity For Interactive Image Segmentation[C]∥2010 IEEE Confe-rence on Computer Vision and Pattern Recognition(CVPR).2010:3129-3136
[13] Wang Chun-yao,Chen Jun-zhou,Li Wei.Superpixel segmentation algrithms review[J].Application Research of Computers,2014,31(1):6-12(in Chinese) 王春瑶,陈俊周,李炜.超像素分割算法研究综述[J].计算机应用研究,2014,31(1):6-12
[14] Arbelez,Pablo,Maire M,et al.Contour Detection and Hierar-chical Image Segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(5):898-916

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!