作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (11): 197-199. doi: 10.3969/j.issn.1000-3428.2011.11.068

• 人工智能及识别技术 • 上一篇    下一篇

基于多特征融合和极坐标变换的目标识别

高文琦a,张复春a,李 雁a,苏清贺b   

  1. (中国人民解放军空军航空大学 a. 航空理论系;b. 特种专业系,长春 130022)
  • 收稿日期:2010-11-04 出版日期:2011-06-05 发布日期:2011-06-05
  • 作者简介:高文琦(1986-),女,硕士研究生,主研方向:模式识别,信息处理;张复春,教授;李 雁、苏清贺,硕士研究生

Target Recognition Based on Multi-feature Fusion and Polar Coordinates Transformation

GAO Wen-qi  a, ZHANG Fu-chun  a, LI Yan  a, SU Qing-he  b   

  1. (a. Department of Aviation Theory; b. Department of Specialty, Aviation University of Air Force, Changchun 130022, China)
  • Received:2010-11-04 Online:2011-06-05 Published:2011-06-05

摘要: 提出一种基于多特征融合和极坐标变换的目标识别方法。利用多特征融合方法,从原始图像中提取待识别目标实现维数压缩任务;引入极坐标变换和快速傅里叶变换相结合的方法,确定变换后的不变特征矩阵;通过计算不变特征矩阵和模板特征矩阵的相关性对目标进行分类识别。实验结果证明,该目标识别方法有较好的可靠性和较高的识别正确率。

关键词: 目标识别, 特征融合, 极坐标, 快速傅里叶变换

Abstract: This paper puts forward a method of target recognition based on multi-feature integration and polar coordinates transformation. It uses multi-feature fusion method to extract from the original image to be identified to achieve the objective dimension of compression tasks. The polar coordinate and Fast Fourier Transform(FFT) method are introduced to determine the invariant features of the transformed matrix. The targets are classified and recognized by calculating the same correlation of the characteristic matrix and the template features matrix. Experimental results show that this method has good reliability and high recognition rate.

Key words: target recognition, feature fusion, polar coordinate, Fast Fourier Transform(FFT)

中图分类号: