• DocumentCode
    699161
  • Title

    Joint power spectrum addition technique for optical color pattern recognition

  • Author

    Islam, Tanwir Zubayer ; Waliullah Khan Nomani, Md ; Bari, Syed Mustafa Khelat ; Rafiqul Haider, Md ; Islam, Mohammed Nazrul

  • Author_Institution
    Dept. of Electr. & Electron. Eng., Bangladesh Univ. of Eng. & Technol., Dhaka, Bangladesh
  • fYear
    2004
  • fDate
    6-10 Sept. 2004
  • Firstpage
    757
  • Lastpage
    760
  • Abstract
    An improved fringe-adjusted joint transform correlator based technique for optical color pattern recognition is proposed. In this proposed technique, a joint color image is processed through three channels. The joint power spectrum (JPS) of each channel-component is obtained by Fourier transform operation. The JPS of the individual channels are then added to obtain the overall JPS. After applying the Fourier plane subtraction to the overall JPS, it is passed through a color fringe-adjusted filter to produce excellent correlation discrimination. The implementation complexity is reduced as the filtering and the inverse Fourier transform processed through only one channel. Opto-electronic implementation of the proposed technique is presented that can be applied in real time color pattern recognition for practical applications.
  • Keywords
    Fourier transforms; correlation methods; filtering theory; image colour analysis; image recognition; inverse transforms; real-time systems; Fourier plane subtraction; JPS; channel-component; color fringe-adjusted filter; correlation discrimination; fringe-adjusted joint transform correlator based technique; inverse Fourier transform; joint power spectrum addition technique; optical color pattern recognition; optoelectronic implementation; real-time recognition; Abstracts; Color; Correlation; Lasers; Switching circuits; TV; Transforms;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing Conference, 2004 12th European
  • Conference_Location
    Vienna
  • Print_ISBN
    978-320-0001-65-7
  • Type

    conf

  • Filename
    7079691