电子学报 ›› 2016, Vol. 44 ›› Issue (5): 1247-1253.DOI: 10.3969/j.issn.0372-2112.2016.05.034

• 科研通信 • 上一篇    下一篇

基于同底三角形面积描述的形状检索

胡大盟, 黄伟国, 杨剑宇, 朱忠奎   

  1. 苏州大学城市轨道交通学院, 江苏苏州 215131
  • 收稿日期:2014-10-21 修回日期:2015-02-27 出版日期:2016-05-25
    • 通讯作者:
    • 黄伟国
    • 作者简介:
    • 胡大盟 男,1990年生于江苏淮安,硕士研究生,研究方向为计算机视觉.
    • 基金资助:
    • 国家自然科学基金 (No.51405320,No.61305020); 江苏省科研基金 (No.BK20130316)

Common Base Triangle Area Representation Method for Shape Retrieval

HU Da-meng, HUANG Wei-guo, YANG Jian-yu, ZHU Zhong-kui   

  1. School of Urban Rail Transportation, Soochow University, Suzhou, Jiangsu 215131, China
  • Received:2014-10-21 Revised:2015-02-27 Online:2016-05-25 Published:2016-05-25
    • Supported by:
    • National Natural Science Foundation of China (No.51405320, No.61305020); Research Fund of Jiangsu Province (No.BK20130316)

摘要:

为了在形状匹配的过程中提高形状特征对边界噪声和图像变形的鲁棒性,同时兼顾形状匹配算法的检索精度和运算效率,提出一种基于同底三角形面积的形状匹配方法.该方法首先计算每个轮廓采样点的同底三角形面积描述子,并对该描述子进行局部平滑,使其更加鲁棒.然后采用加权L1度量方法计算两个形状所有轮廓点的同底三角形描述子之间的距离,获得匹配代价矩阵.最后利用动态规划算法计算匹配代价矩阵的相似度,获得形状距离,实现形状匹配.通过在MPEG-7、Kimia以及铰接形状数据库上测试分析表明,该方法对变形目标具有良好的鲁棒性,且提高了运算效率和检索精度.

关键词: 同底三角形, 局部平滑, 动态规划, 混合检索, 形状匹配

Abstract:

To solve the problem of contour noise and deformation in shape matching, a novel method based on common base triangle area for improving retrieval accuracy and computational efficiency is proposed.Firstly, a common base triangle area descriptor of each sample point is defined based on the area functions of the triangles formed by the other sample points and its two neighbor points.Then the descriptor is local smoothed to keep more compact and robust.Secondly, a match cost matrix is obtained by computing the common base triangle area descriptors of all the sample points on two shapes.Finally, the distance between two shapes is measured based on the match cost matrix by DP algorithm.The experimental results of MPEG-7, Kimia and the articulation shape database indicate that this method is robust to the contour deformation, and the computational efficiency and the retrieval accuracy are all essentially improved.

Key words: common base triangle, local smoothing, dynamic programming, mixed retrieval, shape matching

中图分类号: