计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (2): 143-145.DOI: 10.3778/j.issn.1002-8331.2011.02.044

• 图形、图像、模式识别 • 上一篇    下一篇

应用R变换和奇异值分解的剪纸纹样识别

王晓云1,韦月琼2,李国祥3,秦芳远3,张显全3   

  1. 1.长江师范学院 数学与计算机学院,重庆 408100
    2.广西广播电视监测中心,南宁 530022
    3.广西师范大学 计算机科学系,广西 桂林 541004
  • 收稿日期:2009-08-11 修回日期:2009-11-26 出版日期:2011-01-11 发布日期:2011-01-11
  • 通讯作者: 王晓云

Paper cut-out patterns recognition using R-transform and SVD

WANG Xiaoyun1,WEI Yueqiong2,LI Guoxiang3,QIN Fangyuan3,ZHANG Xianquan3   

  1. 1.College of Mathematics & Computer Science,Yangtze Normal University,Chongqing 408100,China
    2.Guangxi Administration of Radio and Television Monitoring Center,Nanning 530022,China
    3.Department of Computer Science,Guangxi Normal University,Guilin,Guangxi 541004,China
  • Received:2009-08-11 Revised:2009-11-26 Online:2011-01-11 Published:2011-01-11
  • Contact: WANG Xiaoyun

摘要: 首先对剪纸纹样进行R变换,求出峰值数,对R变换数据进行归一化处理,通过奇异值分解得到图像识别的特征向量,根据特征向量值和峰值数对剪纸纹样的识别。使用该方法提取到的特征向量具有平移、旋转和尺度不变性,能较好地识别有一定艺术夸张变形的剪纸纹样。

关键词: R变换, 奇异值分解, 特征提取, 纹样识别

Abstract: The paper-cut patterns are transformed by an R-transform.And then the result of R-transform is normalized.Through SVD eigenvector of image recognition can be gotten.The paper-cutting patterns are recognized according to the peak value and the characteristic vector.The experiment proves that this algorithm is invariant to rotation,scale and translation as well as suitable for the recognition of paper-cutting patterns.

Key words: R-transform, Sigular Value Decomposition(SVD), feature extraction, patterns recognition

中图分类号: