基于傅里叶-极坐标变换的相关结果后处理技术

甘厚吉, 华文深

甘厚吉, 华文深. 基于傅里叶-极坐标变换的相关结果后处理技术[J]. 应用光学, 2010, 31(6): 939-942.
引用本文: 甘厚吉, 华文深. 基于傅里叶-极坐标变换的相关结果后处理技术[J]. 应用光学, 2010, 31(6): 939-942.
shu
GAN Hou-ji, HUA Wen-shen. Post processing technique for correlation results based on Fourier-polar transformation[J]. Journal of Applied Optics, 2010, 31(6): 939-942.
Citation: GAN Hou-ji, HUA Wen-shen. Post processing technique for correlation results based on Fourier-polar transformation[J]. Journal of Applied Optics, 2010, 31(6): 939-942.
shu

基于傅里叶-极坐标变换的相关结果后处理技术

  • 军械工程学院光学与电子工程系,河北石家庄050003

详细信息
    通讯作者:

    甘厚吉(1981-)，男，湖北襄樊人，博士研究生，主要从事图像处理与光学相关识别的研究工作。

  • 中图分类号: TN919.8;TP391.4

Post processing technique for correlation results based on Fourier-polar transformation

  • Department of Optics and Electronic Engineering,Ordnance Engineering College,Shijiazhuang 050003,China

摘要

    摘要
  • 摘要: 在光学相关识别中，对相关输出结果进行后处理是保证图像识别准确性的关键之一。研究者通常采用神经网络技术对相关输出结果进行处理，并取得了较好的效果，但它需要预先准备大量的相关峰和噪声峰训练样本。根据极坐标变换能将笛卡尔坐标系下的旋转转变成平移的性质以及傅里叶变换的平移不变性，提出一种基于傅里叶-极坐标变换的相关结果后处理方法。验证结果表明：目标的旋转图像与目标自身的傅里叶-极坐标变换的相似度较大，而干扰图像与目标的傅里叶极坐标变换的相似度较小。本文的方法在后处理阶段可对目标和干扰进行有效的分类识别，而且还能避免对相关峰和噪声峰训练样本的收集，从而使得光学相关识别系统的应用更加便利。
    Abstract: In optical correlation recognition, the post-processing of correlation output results is one of the key steps to ensure the correctness of image recognizing. Neural network technique is usually used to post-process correlation output results and good result is obtained, however, this method needs to prepare a lot of training samples of correlation peaks and noise peaks in advance. Based on the polar coordinates transformations capability of transforming the rotation in Cartesian coordinate into translation and the translation invariant property of Fourier transformation, a post-processing method of correlation results based on Fourier-polar transformation is proposed. The verification results indicate that the similarity between the Fourier-polar transformations of target and its rotated images is greater compared to the similarity between the Fourier-polar transformations of target and disturbances. So the proposed method can effectively distinguish between targets and disturbances at the post processing stage, and it can avoid collecting training samples, which makes optical correlation recognition system convenient to be applied.
    • HTML全文
    • 参考文献(1)
  • ［1］李豫华,回红,刘锡久,等.纯相位二值化匹配滤波器的优化设计［J］.中国激光,1999,26(10):897-901.
    LI Yu-hua, HUI Hong, LIU Xi-jiu, et al. Optimized design of binary phase-only matched filters［J］. Chinese Journal of Lasers, 1999,26(10):897-901. (in Chinese with an English abstract)
    ［2］沈学举, 王永仲, 姚广涛. 非约束纯相位空间匹配滤波器设计研究［J］. 光子学报, 2007,36(5):945-949.
    SHEN Xue-ju, WANG Yong-zhong, YAO Guang-tao. Research on unconstrained phase-only matched filtering design［J］. Acta Photonica Sinica,2007,36(5):945-949. (in Chinese with an English abstract)
    ［3］王永仲, 薛蕊, 华文深, 等.旋转不变匹配滤波相关识别的振幅补偿滤波优化算法研究［J］.激光杂志,2005,26(3):65-66.
    WANG Yong-zhong, XUE Rui, HUA Wen-shen, et al. Optimal arithmetic of amplitude-compensated filter for rotation invariant pattern recognition［J］. Laser Journal, 2005,26(3):65-66. (in Chinese with an English abstract)
    ［4］袁祥岩, 陶纯堪, 于大勇, 等. 位相编码振幅调制联合变换相关器的设计［J］. 中国激光, 2003,30(2):149-153.
    YUAN Xiang-yan, TAO Chun-kan, YU Da-yong, et al. Phase-encoded joint transform correlator by use of amplitude-modulation［J］. Chinese Journal of Lasers, 2003,30(2):149-153. (in Chinese with an English abstract)
    ［5］HONG Ru-tong,CHEN Ren-yuan,HONG En.New signal post-processing technique to 3-D object distortion-invariant correlation recognition［J］.SPIE,1998,3466:324-330.
    ［6］王永仲,张勇,冯广斌,等.BP神经网络在光学相关器相关峰识别中的应用［J］. 应用光学, 2006,27(1):15-18.
    WANG Yong-zhong, ZHANG Yong, FENG Guang-bin, et al. Application of BP neural network in correlated of optical correlator peak recognition［J］. Journal of Applied Optics, 2006,27(1):15-18. (in Chinese with an English abstract)
    ［7］齐文辉,阙立志,宋继东.基于BP神经网络的相关识别［J］. 实验室研究与探索, 2009,28(4):56-74.
    QI Wen-hui, QUE Li-zhi, SONG Ji-dong. Correlation recognition based on BP neural network［J］. Research and Exploration in Laboratory, 2009,28(4):56-74. (in Chinese with an English abstract)
    ［8］李海超, 张广军. 基于等高线和Fourier-Polar变换的3-D地形匹配导航方法［J］. 宇航学报, 2008,29(4):1239-1244.
    LI Hai-chao, ZHANG Guang-jun. The novel 3-D terrain matching navigation algorithm based on contour map and Fourier-polar transform［J］. Journal of Astronautic, 2008,29(4):1239-1244. (in Chinese with an English abstract)
    ［9］甘厚吉, 华文深, 王金玉. 常规综合鉴别函数的改进［J］.应用光学, 2007, 28(3):376-379.
    GAN Hou-ji, HUA Wen-shen, WANG Jin-yu. Improvement of conventional synthetic discriminant function［J］. Journal of Applied Optics,2007,28(3):376-379. (in Chinese with an English abstract)
    ［10］CASASENT D, NEHEMIAH A. Confuser rejection performance of EMACH filters for MSTAR ATR［J］. SPIE, 2006, 6245:62450D-1-62450D-12.
    • 相关文章
    • 施引文献
    • 资源附件(0)
计量
  • 文章访问数:  4754
  • HTML全文浏览量:  162
  • PDF下载量:  1018
  • 被引次数: 0
出版历程
  • 刊出日期:  2010-11-30

目录

摘要
HTML全文
    参考文献(1)
    相关文章
    施引文献
    资源附件(0)

    /

    返回文章
    返回

    相关数据库

    广告合作

    友情链接

    帮助中心

    扫描关注本刊微信平台

    您是第  2908769位访问者，欢迎！

    地址: 西安市电子三路西段9号 邮政编码: 710065 联系电话: 029-88288172

    版权所有 © 《应用光学》编辑部

    陕公网安备 61011302001501号       陕ICP备19002862号-1

    北京仁和汇智信息技术有限公司 开发  技术支持: info@rhhz.net   百度统计