The investigation of correlator systems utilizing object and frequency space filters

  • Hui Zhang

    Student thesis: Doctoral Thesis


    The aim of this research is to develop real-time object recognition systems which are robust and have good discrimination. An important aspect of this work is the development of a rotationally invariant optical correlator.

    Optical correlation systems are investigated for the purpose of high speed, high discriminant and distortion invariant pattern recognition. A photorefractive joint transform correlator (JTC) using Bismuth Silicon Oxide (BSO) as a non-linear recording medium and a liquid crystal television as a spatial light modulator is implemented. The underlying physics is considered, some specific techniques to improve the operation are proposed.

    The properties of photorefractive BSO are investigated for use as the dynamic holographic recording medium in information processing systems. The moving grating technique is used for edge-enhanced image reconstruction and for making the correlation peak sharper. The object and frequency space filtering methods are presented to improve the correlation performance, the discrimination, and to realise distortion invariant pattern recognition.

    Circular harmonic matched filters and phase-only filters with different expansion orders are involved in the photorefractive JTC for real-time rotationally invariant pattern recognition. These filters can also be used to track an object with different orientations.

    The coherent triple joint transform correlator employs a third beam to modify the Fourier spectrum and hence improves the correlation performance. In the incoherent triple JTC, the wavelet transform is used in the Fourier domain to achieve a high signalto-noise ratio, noise robustness as well as discrimination. Several wavelet functions are also used, after processing, in the conventional JTC for high-speed image feature extraction. The wavelet transform functions can also be used in the JTC with circular harmonic filters to improve the output quality of rotation invariant pattern recognition.
    Date of AwardNov 2000
    Original languageEnglish
    SupervisorColin M. Cartwright (Supervisor) & W. Allan Gillespie (Supervisor)

    Cite this