期刊文献+

基于边缘特征学习的自然图像对称轴检测 被引量:2

Symmetry Detection in Natural Images via Edge Feature Learning
下载PDF
导出
摘要 主要研究计算机视觉中一个非常具有挑战性的问题——自然图像中对称轴的检测.由于图像中杂乱的场景和物体形态的变化,使得在自然图像中判断像素是否处于对称轴上是非常困难的.为了解决这个难题,考虑到边缘与对称轴的互补关系,提出了2种边缘特征用于帮助对称轴的检测.2种特征都定义在成对的边缘上,分别是为了找到边缘强度高和到对称轴距离相等的成对的边缘.在多尺度和多角度上提取这2种边缘特征,把它们与底层描述子(颜色、亮度、纹理等)差分特征结合在一起,在多示例学习的框架下检测自然图像中的对称轴.在SYMMAX300数据集上的实验结果证明了2种边缘特征能够提升对称轴检测的性能. This paper studies symmetry detection in natural images,which is a challenging problem in computer vision.To differentiate symmetry and non-symmetry in natural images is intractable due to the large variation in objects and the cluttered scene.To address this problem,two types of edge features motivated by the fact that symmetries are complementary to edges are proposed.These two types of features are both defined on pairs of edges to search pairs of edges with consistent high strength and equal distances to symmetries,respectively.The proposed edge features at multiple scales and orientations and integrate them with low level cues (color,brightness and texture) under a multiple instance learning framework to detect symmetries are extracted.The experimental results on SYMMAX300 dataset demonstrate that both proposed edge features can improve performance of symmetry detection.
出处 《上海大学学报(自然科学版)》 CAS CSCD 北大核心 2014年第6期715-725,共11页 Journal of Shanghai University:Natural Science Edition
基金 国家自然科学基金资助项目(61303095) 高等学校博士学科点专项科研基金资助项目(20133108120017) 上海高校青年教师培养资助计划(ZZSD13005)
关键词 对称轴 对称轴检测 边缘 多示例学习 底层特征 symmetry axis symmetry detection edge multiple instance learning low level feature
  • 相关文献

参考文献13

  • 1BAI X, LATECKI L J, LIU W. Skeleton pruning by contour partitioning with discrete curve evolution [J]. IEEE Trans PAMI, 2007, 29(3): 449-462.
  • 2BAI X, LATECKI L J. Path similarity skeleton graph matching [J].IEEE Trans PAMI, 2008 30(5): 1282-1292.
  • 3BAI X, WANG X, LATECKI L J, et al. Active skeleton for non-rigid object detection [C]// International Conference on Computer Vision. 2009: 575-582.
  • 4SIDDIQI K, PIZER S. Medial representations [M]. Berlin: Springer-Verlag, 2009.
  • 5TSOCKAS S, KOKK1NOS I. Learning-based symmetry detection in natural images [C]// European Conference on Computer Vision. 2012: 41-45.
  • 6MAR;FIN D, FOWLKES C, TAL D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics [C]// International Conference on Computer Vision. 2001: 416-423.
  • 7MARTIN D, FOWLKES C, MALIK J. Learning to detect natural image boundaries using local brightness, color, and texture cues [J]. IEEE Trans PAMI, 2004, 26(5): 530-549.
  • 8刘超,安平,赵冰,闫吉辰,张兆杨.基于边缘的面向虚拟视绘制的深度编码算法[J].上海大学学报(自然科学版),2014,20(4):450-457. 被引量:1
  • 9RUBNER Y, PUZICHA J, TOMASI C, et al. Empirical evaluation of dissimilarity measures for color and texture [C]// International Conference on Computer Vision. 1999: 1165-1172.
  • 10REN X. Multi-scale improves boundary detection in natural images [C]// European Conference on Computer Vision. 2008: 533-545.

二级参考文献17

  • 1HE X,JIN X,WANG M H,et al.A novel depth-Image based view synthesis scheme for multiview and 3DTV[J].Computer Science,Advances in Multimedia Modeling,2011,6523:161-170.
  • 2DARIBO I,SAITO H.A novel inpainting-based layered depth video for 3DTV[J].IEEE Transactions on Broadcasting,2011,57(2):533-541.
  • 3FEHN C.Depth-image-based rendering(DIBR),compression and transmission for a new approach on 3DTV[C]//Proceedings in SPIE Stereoscopic Displays and Virtual Reality Systems Ⅺ.2004:93-104.
  • 4SHAO F,JIANG G Y,MEI H,et al.Asymmetric coding of multi-view video plus depth based 3-D video for view rendering[J].IEEE Transactions on Multimedia,2012,14(1):157-167.
  • 5WANG Z,ZHOU J.A novel approach for depth image based rendering,based on non-linear transformation of depth values[C]//2011 International Conference on Image Analysis and Signal Processing.2011:138-142.
  • 6MERKLE P,MORVAN Y,SMOLIC A,et al.The effects of multiview depth video compression on multiview rendering[J].Signal Processing:Image Communication,2009,24:73-88.
  • 7MORVAN Y,FARIN D,PETER H,et al.Depth-image compression based on an R-D optimized quadtree decomposition for the transmission of multiview images[C]//IEEE International Conference on Image Processing.2007:105-108.
  • 8LIU S J,LAI P L,TIAN D,et al.Joint trilateral filtering for depth map compression[C]//Proc SPIE,Visual Communications and Image Processing 2010.2010,DOI:10.1117/12.863341.
  • 9EFFENDI L P.Non-geometric distortion smoothing approach for depth map preprocessing[J].IEEE Transactions on Multimedia,2011,13(2):246-254.
  • 10LEE P J,HUANG X X.3D motion estimation algorithm in 3D video coding[C]//2011 International Conference on System Science and Engineering.2011:338-341.

同被引文献20

引证文献2

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部