arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1104.2745cs.CV
收藏

一种用于识别的基于轴的表示方法

An Axis-Based Representation for Recognition

Middle East Technical University(中东科技大学)

Cagri Aslan, Sibel Tari

摘要:

本文提出了一种新的基于轴的形状表示方案,以及匹配框架,以解决通用形状识别的问题。其主要思想是在形心坐标系中定义局部对称轴的相对空间排列及其度量性质。由此产生的描述是不变的比例,旋转,在视点和关节的小变化。对称点是从曲面中提取的,曲面的水平曲线通过曲率粗略地模拟了运动。通过增加对演化曲线的平滑量,仅提取对应于形状的最突出部分的那些对称轴。该表示不受传统的连接骨架的常见的不稳定性问题。它很好地捕捉了形状的感知特性。因此,找到形状之间的相似性和差异变得更容易。匹配过程在不同的2D形状数据库上给出了非常成功的结果。

英文摘要:

This paper presents a new axis-based shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted. The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual qualities of shapes well. Therefore finding the similarities and the differences among shapes becomes easier. The matching process gives highly successful results on a diverse database of 2D shapes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑