基于一维傅里叶变换的改进形状上下文特征

doi:10.3969/j.issn.0253-2778.2010.10.011

中国科学技术大学学报 ›› 2010, Vol. 40 ›› Issue (10): 1065-1073.DOI: 10.3969/j.issn.0253-2778.2010.10.011

基于一维傅里叶变换的改进形状上下文特征

李珊珊

1.中国科学技术大学电子工程与信息科学系，安徽合肥 230027；2.长安大学电子信息工程系，陕西西安 710064

收稿日期:2009-09-10 修回日期:2010-01-12 出版日期:2010-10-31 发布日期:2010-10-31
通讯作者: 吴秀清
作者简介:李珊珊，女，1982年生，博士. 研究方向：图像分析，计算机视觉. E-mail: ssnl@mail.ustc.edu.cn

Improved shape context based on 1-D fourier transformation

LI Shanshan

1.Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China; 2.Department of Electronic Information Engineering, Changan University, Xian 710064, China

Received:2009-09-10 Revised:2010-01-12 Online:2010-10-31 Published:2010-10-31

摘要/Abstract

摘要： 提出了一种新的特征描述子，将无方向选择的形状上下文特征看做一系列一维信号的集合，对这些信号做一维傅里叶变换，理论上证明了利用这种简单的算法可以生成平移、缩放、旋转不变的特征.新特征的提取运算简单，时间复杂度低.形状点集匹配的实验结果验证了这种新特征的有效性.

关键词: 一维傅里叶变换, 形状上下文, 旋转不变性

Abstract: A new shape feature descriptor was proposed, which considers shape context features as an array of 1-D signals. The 1-D Fourier transformation was then performed on every signal. The new feature descriptor has been proved theoretically to be invariant for scaling, translation and rotation, with acceptable computational complexity. Shape point matching experiment shows the efficiency and effectiveness of the new feature descriptor.

Key words: 1-D Fourier transformation, shape context, rotation invariant

李珊珊，吴秀清. 基于一维傅里叶变换的改进形状上下文特征[J]. 中国科学技术大学学报, 2010, 40(10): 1065-1073.

LI Shanshan, WU Xiuqing. Improved shape context based on 1-D fourier transformation[J]. Journal of University of Science and Technology of China, 2010, 40(10): 1065-1073.

基于一维傅里叶变换的改进形状上下文特征

Improved shape context based on 1-D fourier transformation

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价