知识组织

采用几何特征的人造物体图像检索研究

  • 李宇翔 ,
  • 费世英 ,
  • 李端明
展开
  • 西南科技大学经济管理学院
李宇翔,西南科技大学经济管理学院副教授,E-mail:eclili@foxmail.com;费世英,西南科技大学经济管理学院硕士研究生;李端明,西南科技大学经济管理学院教授,研究生导师。

收稿日期: 2012-09-17

  修回日期: 2012-11-18

  网络出版日期: 2013-02-05

Research on Image Retrieval of Artificial Object Based on Geometric Features

  • Li Yuxiang ,
  • Fei Shiying ,
  • Li Duanming
Expand
  • Institute of Economics and Management, Southwest University of Science and Technology, Mianyang 621010

Received date: 2012-09-17

  Revised date: 2012-11-18

  Online published: 2013-02-05

摘要

修正传统图像信息描述方法,在人造物体图像解释过程中采用几何特征和先验知识相结合的方法,提出人造物体图像结构描述以及相应的匹配算法。通过特征点对目标图像的形状轮廓进行离散化和曲线拟合获取离散曲线段的几何特征向量,并根据特征点类型来描述曲线段之间的关系,最终还原人造物体图像结构描述的参数化模型。实验证明,该方法更能够满足人类的视觉特性,而且能够方便计算机还原出图像中的对象形状。

本文引用格式

李宇翔 , 费世英 , 李端明 . 采用几何特征的人造物体图像检索研究[J]. 图书情报工作, 2013 , 57(03) : 112 -119 . DOI: 10.7536/j.issn.0252-3116.2013.03.021

Abstract

To qualify the method of traditional description of image, this paper combines geometric features with prior knowledge in artificial image recognition process, and proposes the method of structure description of artificial object image and the corresponding matching algorithm. It makes the graph structure of object discretization by feature points, and obtains its geometric characteristics with curve fitting. Then it describes the relationships of curves by the types of feature points, and develops the parametric model to restore the object in the image. Experimental results show that the description method has better human vision and can help computer easily restore the shape of the object in the image.

参考文献

[1] 安志勇.基于内容的图像检索关键技术研究.西安:西安电子科技大学,2008.

[2] 张恒博.基于内容的图像数据库检索的技术研究.大连:大连理工大学,2008.

[3] 高如如.基于内容的图像检索技术研究.合肥:中国科学技术大学,2011.

[4] 向友君,谢胜利.图像检索技术综述[J].重庆邮电学院学报,2006,18(3):348-354.

[5] 曾智勇.基于内容图像数据库检索中的关键技术研究.西安:西安电子科技大学,2006.

[6] 江悦.场景图像内容表述和分类研究.北京:国防科学技术大学,2010.

[7] 黄诚,王国营.一种基于颜色聚合向量的图像检索方法[J].计算机工程,2006,32(2):194-199.

[8] 刘丽,匡纲要. 图像纹理特征提取方法综述[J].中国图象图形学报, 2009, 14(4): 622-635.

[9] Salih N D,Ngo D C L.An efficient boundary-based approach for shape representation//2nd International Conference on Information and Communication Technologies.Melaka:Multimedia University,2006:1504-1509.

[10] 陈君,王庆.基于图割和显著性的图像结构表示方法研究[J].计算机应用研究,2009,26(9):3589-3592.

[11] 张伟.基于特征值分解的图像边界与空间关系描述[J].计算机工程,2011,37(10):201-225.

[12] 何莲,蔡敬菊,张启衡.多边形近似及形状匹配的二维目标检测[J].激光与红外,2011,41(6):699-705.

[13] Luo Bin, Hancock R E. Structural graph matching using the EM algorithm and singular value decomposition[J].Pattern Analysis and Machine Intelligence, 2001,23(10):1120-1136.

[14] Yang Lin, Teng Zhongjian.A novel approach for image representation and matching based on mixed graph structure//International Conference on Computational Intelligence and Software Engineering.Fuzhou: Fujian Normal University,2009:1-4.

[15] Zhao Haifeng, Kong Min, Luo Bin. Hierarchical shape representation based on polar-graph spectra//International Conference on Intelligent Computing.Berlin:Springer Berlin Heidelberg, 2006:900-905.

[16] Mauro C, Diligenti M, Gori M. Similarity learning for graph based image representation [J]. Pattern Recognition Letters,2003, 24(8):1115-1122.

文章导航

/