Pattern recognition with moment invariants: A comparative study and new results

https://doi.org/10.1016/0031-3203(91)90140-ZGet rights and content

Abstract

Moment invariants have been proposed as pattern sensitive features in classification and recognition applications. In this paper, the authors present a comprehensive study of the effectiveness of different moment invariants in pattern recognition applications by considering two sets of data: handwritten numerals and aircrafts.

The authors also present a detailed study of Zernike and pseudo Zernike moment invariants including a new procedure for deriving the moment invariants. In addition, the authors introduce a new normalization scheme that reduces the large dynamic range of these invariants as well as implicit redundancies in these invariants.

Based on a comprehensive study with both handwritten numerals and aircraft data, the authors show that the new method of deriving Zernike moment invariants along with the new normalization scheme yield the best overall performance even when the data are degraded by additive noise.

References (35)

  • D. Casasent et al.

    Image segmentation and real image tests for an optical moment-based feature extractor

    Optics Communs

    (1984)
  • M. Hu

    Visual pattern recognition by moment invariants

    IRE Trans. Inf. Theory

    (1962)
  • S. Dudani et al.

    Aircraft identification by moment invariants

    IEEE Trans. Comput.

    (1977)
  • R. Gonzalez et al.

    Digital Image Processing

  • R. Bamieh et al.

    A general moment invariants/attributed-graph method for the three dimensional object recognition from a single image

    IEEE J. Robotics Automation

    (1986)
  • S. Reddi

    Radial and angular moment invariants for image identification

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1981)
  • S. Maitra

    Moment invariants

  • D. Casasent et al.

    Optical system to compute intensity moments: design

    Appl. Optics

    (1982)
  • M. Teague

    Calculation of irradiance moments

    Appl. Optics

    (1980)
  • D. Casasent et al.

    Hybrid processor to compute invariant moments for pattern recognition

    Optics Lett.

    (1980)
  • Z. Budrikis et al.

    Moment calculations by digital filters

    ATT Bell Labs Tech. J.

    (1984)
  • M. Teague

    Image analysis via the general theory of moments

    J. Opt. Soc. Am.

    (1980)
  • Y. Abu-Mustafa et al.

    Recognitive aspects of the moment invariants

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1984)
  • Y. Abu-Mustafa et al.

    Image normalizations by complex moments

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1984)
  • A. Reeves et al.

    Three dimensional shape analysis using moments and Fourier descriptors

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1988)
  • C. Teh et al.

    On image analysis by the methods of moments

    IEEE Trans. Pattern Anal. Mach. Intell.

    (1988)
  • A. Bhatia et al.

    On the circle polynomials of Zernike and related orthogonal sets

  • Cited by (461)

    • Solving inverse-PDE problems with physics-aware neural networks

      2021, Journal of Computational Physics
      Citation Excerpt :

      This is also advantageous from a physics point of view, because domain's knowledge of hidden fields can be naturally formulated in terms of basis functions into this framework. One such family of series expansions are the moment-based methods that have been largely exploited in image reconstruction [40,5,64,3]. In particular, Zernike moments [84] provide a linearly independent set of polynomials defined on the unit circle/sphere in two/three spatial dimensions.

    View all citing articles on Scopus
    View full text