Invariant Spectroscopic Pattern Recognition Using Mellin Transforms. Selby, M. & Hughes, R. J. Analytical Chemistry, 66(22):3925--3936, November, 1994.
Invariant Spectroscopic Pattern Recognition Using Mellin Transforms [link]Paper  doi  abstract   bibtex   
Image descriptors based on the circular-Fourier-radial-Mellin transform are used for position-, rotation-, scale-, and intensity-invariant multiclass pattern recognition. The orders of the radial moments and of the circular harmonics are chosen to obtain an efficient image description. The first-order radial moments of three circular harmonics are sufficient to obtain a satisfactory recognition performance. The influence of additive noise is investigated. Experimental results are shown.
@article{ selby_invariant_1994,
  title = {Invariant Spectroscopic Pattern Recognition Using Mellin Transforms},
  volume = {66},
  url = {http://pubs.acs.org/doi/abs/10.1021/ac00094a013},
  doi = {10.1021/ac00094a013},
  abstract = {Image descriptors based on the circular-Fourier-radial-Mellin transform are used for position-, rotation-, scale-, and intensity-invariant multiclass pattern recognition. The orders of the radial moments and of the circular harmonics are chosen to obtain an efficient image description. The first-order radial moments of three circular harmonics are sufficient to obtain a satisfactory recognition performance. The influence of additive noise is investigated. Experimental results are shown.},
  number = {22},
  journal = {Analytical Chemistry},
  author = {Selby, Mark. and Hughes, Roy J.},
  month = {November},
  year = {1994},
  keywords = {biometrics, correlation, fingerprint identification, fingerprint verification, phase, phase-only correlation, phase-only matched filtering},
  pages = {3925--3936}
}

Downloads: 0