Fast Computation of Zernike Moments Using Three Look-up Tables

  • Kim, Sun-Gi (Image Engineering Lab., Department of Electronic Engineering, Hanyang University) ;
  • Kim, Whoi-Yul (Image Engineering Lab., Department of Electronic Engineering, Hanyang University) ;
  • Kim, Young-Sum (Electronics and Telecommunications Research Institute) ;
  • Park, Chee-Hang (Electronics and Telecommunications Research Institute)
  • Published : 1997.12.01

Abstract

Zernike moments have been one of the most commonly used feature vectors for recognizing rotated patterns due to its rotation invariant characteristics. In order to reduce its expensive computational cost, several methods have been proposed to lower the complexity. One of the methods proposed by mukundan and K. R. Ramakrishnan[1], however, is not rotation invariant. In this paper, we propose another method that not only reduces the computational cost but preserves the rotation invariant characteristics. In the experiment, we compare our method with others, in terms of computing time and the accuracy of moment feature at different rotational angle of an object in image.

Keywords

References

  1. Pattern Recognition v.28 no.9 Fast Computation of Legendre and Zernike moments R.Mukundan;K.R.Ramakrishnan
  2. IEEE Conference on Computer Vision and Pattern Recognition A Practical Pattern Recognition System for Translation, Scale and Roration Invariance W.Y.;Kim;Po Yuan
  3. Pattrtn Recognition v.23 no.10 Rotation Invariant Image Recognition Using Features Selected via a Systematic Method A.Khotanzad;Y.Hong
  4. IEEE Trans. On Pattern Analysis and Machine Intelligence v.12 no.5 Invariant Image Recognition by Zernike Moments A.Khotanznd;Y.H.Hong
  5. IRE Trans. Info Theory v.8 no.1 Visual Pattern Recognition by Moment Invariants M.K.Hu
  6. Pattern Recognition Letters v.9 Pattern recognition with moment invariants on machine vision system Z.Mingfa;S.Hasani;S.Bhattarai;H.Singh
  7. Digital Image Processing R.C.Gonzalez;R.Woods
  8. IEEE Conference on Computer Vision and Pattern Recognition Conent-Based Trademark Retrieval System Using Visually Salient Feature Y.S.Kim;W.Y.Kim