Ms. Millan et J. Escofet, FOURIER-DOMAIN-BASED ANGULAR-CORRELATION FOR QUASI-PERIODIC PATTERN-RECOGNITION - APPLICATIONS TO WEB INSPECTION, Applied optics, 35(31), 1996, pp. 6253-6260
A Fourier-domain-based recognition technique is proposed for periodic
and quasiperiodic pattern recognition. It is based on the angular corr
elation of the moduli of the sample and the reference Fourier spectra
centered at the maximum central point. As in other correlation techniq
ues, recognition is achieved when a high correlation peak is obtained,
and this result occurs when the two spectra coincide. The angular cor
relation is a one-dimensional function of the rotation angle. The posi
tion of the correlation peak indicates the rotation angle between two
similar patterns in the original images. Some optimizations for the di
screte calculation of the Fourier-domain-based angular correlation are
also proposed. Some applications of this technique to web inspection
tasks, such as pattern recognition and classification, damaged web eva
luation, and detection of defects, are presented and discussed. (C) 19
96 Optical Society of America