张建宇,张荣国,胡静,刘小君,王芳,李晓明

• 1:太原科技大学计算机科学与技术学院
• 2:合肥工业大学机械工程学院

摘要(Abstract)：

针对结构敏感性超像素不能很好贴合边界的问题,提出了一种带边界项的结构敏感性超像素图像分割方法。该方法在考虑结构敏感性的同时引入边界项,通过边界项来计算当前像素落在图像真实边界上的可能性,重新分配和优化超像素边界,使得超像素分割边界和实际边界尽可能贴合,保证在结构敏感区域生成大的超像素,在稀疏区域生成小的超像素。实验采用Berkeley数据集,通过六种考核指标对分割图像进行分析对比,验证了所提方法在召回率、欠分割误差、可实现分割准确度等性能方面有良好的表现。

关键词(KeyWords)： 结构敏感性;超像素分割;边界项

Abstract:

Keywords:

基金项目(Foundation): 国家自然基金(51875152);; 山西省自然基金(201801D121134);; 晋城市科技局项目(201501004-5)

作者(Author): 张建宇,张荣国,胡静,刘小君,王芳,李晓明

参考文献(References)：

• [1] REN X,MALIK J. Learning a classification model for segmentation[J]. Proceedings of the Ninth IEEE International Conference on,IEEE,2003:10-17.
• [2] LI Z,WU M X,CHANG S F. Segmentation using superpixels:A bipartite graph partitioning approach[C]//Computer Vision&Pattern Recognition. IEEE,2012:789-796.
• [3] SCHICK A,BAUML M,STIEFELHAGEN R. Improving foreground segmentations with probabilistic superpixel Markov random fields[C]//Computer Vision&Pattern Recognition Workshops. IEEE,2012:16-21.
• [4] SATO H. Discriminant saliency,the detection of suspicious coincidences,and applications to visual recognition[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence,2009,31(6):989-1005.
• [5]张荣国，刘小君，董磊，等．物体轮廓形状超像素图割快速提取方法[J]．模式识别与人工智能，2015,28(4):344-353.
• [6] FULKERSO B,VEDALDI A,SOATTO S. Class segmentation and object localization with superpixel neighborhoods[C]//Computer Vision,2009 IEEE 12th. International Conference on IEEE,2009.
• [7]张荣国，高静雅，李富萍，等．基于水平集的脑MR图像分割方法[J]．北京工业大学学报，2017,43(2):244-250.
• [8] ARBELAEZ P,MAIRE M,FOWLKES C,et al. Contour Detection and Hierarchical Image Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898-916.
• [9] LI C,ZHENG N,ZHOU G,et al. Video object segmentation with shape cue based on spatiotemporal superpixel neighbourhood[J]. IET Computer Vision,2014,8(1):16-25.
• [10] GALASSO F,CIPOLLA R,SCHIELE B. Video Segmentation with Superpixels[M]. Computer Vision-ACCV 2012,Springer,2012.
• [11] WANG P,ZENG G,WANG J,et al. Structure-Sensitive Superpixels via Geodesic Distance[C]//IEEE International Conference on Computer Vision,ICCV 2011:6-13.
• [12] LIU Y J,YU C C,YU M J,et al. Manifold SLIC:A Fast Method to Compute Content-Sensitive Superpixels[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE,2016.
• [13] ACHANTA R,SHAJI A,SMITH K,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.
• [14] WANG J,JU L,WANG X. An edge-weighted centroidal Voronoi tessellation model for image segmentation[M]. IEEE Press,2009.
• [15] VEREVKA O. Local K-means algorithm for color image quantization[Z]. Proceedings of Graphics Interface 95,Quebec City,Canada,1995:128-136.
• [16] HENDERSON M E. Multiple Parameter Continuation:Computing Implicitly Defined k-manifolds[J]. International Journal of Bifurcation and Chaos,2002,12(3):451-476.
• [17] DU Q,GUNZBURGER F M. Centroidal Voronoi Tessellations:Applications and Algorithms[J]. SIAM Review,1999,41(4):637-676.
• [18] ARBELAEZP,MAIRE M,FOWLKERS C,et al. Contour Detection and Hierarchical Image Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898-916.
• [19] LI Z,CHEN J. Superpixel segmentation using Linear Spectral Clustering[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). IEEE,2015.
• [20] BERGH M V D,BOIX X,ROIG G,et al. SEEDS:Superpixels Extracted via Energy-Driven Sampling[C]//European Conference on Computer Vision. Springer,Berlin,Heidelberg,2012.
• [21] XU C,CORSO J J. Evaluation of super-voxel methods for early video processing[C]//IEEE Conference on Computer Vision&Pattern Recognition. IEEE Computer Society,2012:1202-1209.
• [22] RAND W M. Objective Criteria for the Evaluation of Clustering Methods[J]. Publications of the American Statistical Association,1971,66:846-850.