期刊文献+

一种新的仿射不变特征及其在平面曲线匹配中的应用

A new affine invariant feature and its application in planar curves-matching
原文传递
导出
摘要 构造了一种新的仿射变换不变特征,提出了一种适合于仿射变换的曲线匹配算法。首先将整个轮廓区域进行仿射区域划分,得到一系列子区域质心点;然后将质心和子区域的质心点按规则构成三角形,计算三角形的面积比序列,并将其规范化,构造新的仿射不变特征。在该不变特征的基础上设计新的识别向量和差异度度量函数,通过计算待识别目标与模型曲线之间的差异度来判断是否匹配。理论分析和仿真实验表明,本文方法能成功用于仿射变换下的曲线匹配中,并且对于轮廓相似的物体也能按照差异度大小分别识别出来。 A new invariant feature under affine transformation is given. And then, a new method for matching planar curves under affine transformation is proposed in this paper. First,the affine region is divided for obtaining a series of sub-region's centroids. Then the triangles are constituted by using the whole contour's centroid and sub-region's centroids. The sequences of triangles' area ratios are calculated and normalized. On the basis of the new invariant feature, a new recognition vector matrix is defined, and a different measurement function is defined too. Finally, the different measurement value between model curve and object curve is calculated,which can be employed to judge whether the model and object are matched. Theory analysis and experimental results show that the method is feasible, which can not only match different curves but also distinguish the objects with a similar shape according to different measurement values.
出处 《光电子.激光》 EI CAS CSCD 北大核心 2011年第11期1718-1724,共7页 Journal of Optoelectronics·Laser
基金 国家自然科学基金资助项目(61063030) 江西省自然科学基金资助项目(2010GZS0168) 江西省科技支撑计划资助项目(2009BGA00800) 江西省教育厅资助项目(GJJ11512)
关键词 仿射不变性 平面曲线 匹配 仿射区域划分 affine invariant feature planar curve match affine region dividing
  • 相关文献

参考文献3

二级参考文献32

  • 1潘荣江,孟祥旭,屠长河.一种基于LCS的物体碎片自动拼接方法[J].计算机学报,2005,28(3):350-356. 被引量:16
  • 2徐正伟,吴成柯.空间平面曲线的透视不变性分段[J].计算机学报,1996,19(8):631-635. 被引量:2
  • 3陈涛,蒋咏梅,粟毅,郁文贤.基于压缩映射不动点的图像几何不变特征提取[J].信号处理,2007,23(1):19-26. 被引量:3
  • 4Pikaz A, Dinstein I. Optimal polygonal approximation of digital curves [ J]. Pattern Recognition, 1995, 28(3) : 373-379.
  • 5Chen J M, Ventura J A. Optimization models for shape matching of non-convex polygons [ J ] . Pattern Recognition, 1995, 28 ( 6 ) : 863-877.
  • 6Ayache N, Faugeras O D. HYPER:A new approach for the recognition and positioning of two-dimensional objects[ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8( 1 ) : 44-54.
  • 7Carlsson S. Projectively invariant decomposition and recognition of planar shapes [ J ]. International Journal of Computer Vision, 1996, 17(2) : 193-209.
  • 8Lowe D G.Object recognition from local scale-invariant features[ A ].In:International Conference on Computer Vision[ C ],Corfu,Greece,1999:1150-1157.
  • 9Avid D,Lowe G.Distinctive image features from scale-Invariant keypoints[ J ].International Journal of Computer Vision,2004,60(2):99-114.
  • 10Hu M K.Visual pattern recognition by moment invariants[ J ].IRE Transactions on Information Theory,1962,IT-8(2):179-187.

共引文献16

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