计算机应用 ›› 2013, Vol. 33 ›› Issue (05): 1443-1445.DOI: 10.3724/SP.J.1087.2013.01443

• 多媒体处理技术 • 上一篇    下一篇

局部Radon变换技术及在毛杆折痕识别中的应用

岳洪伟1,2,汪仁煌1,张晶华1   

  1. 1. 广东工业大学 自动化学院,广州 510006
    2. 仲恺农业工程学院 信息学院,广州 510225
  • 收稿日期:2012-11-19 修回日期:2013-01-09 出版日期:2013-05-01 发布日期:2013-05-08
  • 通讯作者: 岳洪伟
  • 作者简介:岳洪伟(1979-),男,安徽亳州人,讲师,博士研究生,主要研究方向: 图像处理、模式识别;汪仁煌(1945-),男,上海人,教授,博士生导师,主要研究方向: 智能测控、信息处理、机器视觉;张晶华(1981-),男,广西玉林人,博士研究生,主要研究方向: 图像处理、模式识别。
  • 基金资助:

    广东省自然科学基金资助项目(S2012010010652);广东省科技计划项目(2012B020314005)

Feather quill crease recognition based on local Radon transform

YUE Hongwei1,2,WANG Renhuang1,ZHANG Jinghua1   

  1. 1. Faculty of Automation, Guangdong University of Technology, Guangzhou Guangdong 510006, China
    2. Information College, Zhongkai University of Agriculture and Engineering, Guangzhou Guangdong 510225, China
  • Received:2012-11-19 Revised:2013-01-09 Online:2013-05-08 Published:2013-05-01
  • Contact: YUE Hongwei

摘要: 针对羽毛杆折痕识别问题,提出一种新的特征提取方法。为了消除Radon变换对缩放平移敏感问题,采用改进的Radon变换提取目标区域的不变矩,并引入局部投影技术消除羽毛杆生理纹理干扰。通过改变尺度因子获得矩不变量矩阵,并采用奇异值分解(SVD)获得特征不变量用于分类识别。实验结果表明该方法具有较强的鲁棒性,具有较高的折痕识别率。

关键词: 羽毛杆折痕, Radon变换, 局部投影, 矩不变量, 图像识别

Abstract: Concerning the recognition of feather quill crease feature, a new feature extraction method was proposed. In order to solve the scaling and translation sensitivity of Radon transform, an improved Radon transform was used to extract moment invariants of target region and local projection technology was adopted to eliminate interference physiological texture of feather quill. Obtaining invariants matrix by changing the scale factor, Singular Value Decomposition (SVD) was provided here to obtain feature invariant for classification and recognition. The results show that this suggested method has higher robustness and higher recognition rate compared with other algorithms.

Key words: feather quill crease, Radon transform, local projection, invariant moment, image recognition

中图分类号: