期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于一维傅里叶变换的改进形状上下文特征 被引量：1

Improved shape context based on 1-D fourier transformation
下载PDF
导出
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. 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.
作者 李珊珊 吴秀清
机构地区 中国科学技术大学电子工程与信息科学系 长安大学电子信息工程系
出处 《中国科学技术大学学报》 CAS CSCD 北大核心 2010年第10期1065-1073,共9页 JUSTC
关键词 一维傅里叶变换 形状上下文 旋转不变性 1-D Fourier transformation shape context rotation invariant
分类号 TP391.41 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献9

  • 1Lowe D G. Object recognition from local scale invariant features [C]// Proceedings of the 7th International Conference on Computer Vision. Kerkyra, Greece: IEEE Press, 1999: 1 150-1 157.
  • 2Dalai D, Triggs B. Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition San Diego, USA: IEEE Computer Society, 2005, 1: 886-893.
  • 3Zheng Y, Doermann D. Robust point matching for non-rigid shapes by preserving local neighborhood structure[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2006, 28(4): 643-649.
  • 4Yang S. Symbol recognition via statistical integration of pixel-level constraint histograms.- A new descriptor [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2005, 27(2):278-281.
  • 5Belongie S, Mori G, Malik J. Matching with shape contexts[C]// Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries. Los Alamitos, CA, USA: IEEE Computer Society, 2000: 1-20.
  • 6Yang S, Wang Y. Rotation invariant shape contexts based on feature-space Fourier transformation[C]// Proceedings of the 4th International Conference on Image and Graphs. Nanjing, China: IEEE Press,2007: 575-579.
  • 7Chui H, Rangarajan A. A new algorithm for non-rigid point matching [J]. Computer Vision and Image Understanding, 2003, 89(2/3): 114-141.
  • 8Super B J. Fast correspondence based system for shape-retrieval [J]. Patten Recognition Letters, 2004, 25(2): 217-225.
  • 9Zhang J, Zhang X, Krim H, et al. Object representation and recognition in shape space [J]. Patten Recognition, 2003, 36(5): 1 143-1 154.

同被引文献5

  • 1格列高里.视觉心理学[M].北京:北京师范大学出版社,1986.208.197-198.155.
  • 2Lowe D G.Object recognition from local scale-invariant features[C]//Proceedings of the International Conference on Computer Vision, 1999 : 1150-1157.
  • 3Belongie S,Mori G,Malik J.Matching with shape con- texts[C]//IEEE Workshop on Content Based Access of Im- age and Video Libraries(CBAIVL-2000),2000.
  • 4Yang Su, Wang Yuanyuan.Rotation invariant shape con- texts based on feature-space Fourier transformation[C]// IEEE Fourth International Conference on Image and Graphs, 2007 : 575-579.
  • 5Chui Haili, Rangarajan A.A new algorithm for non-rigid point matching[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2000,II:44-51.

引证文献1

中国科学技术大学学报
2010年 第10期

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