Title :
Contour Map Registration Using Fourier Descriptors of Gradient Codes
Author_Institution :
Division of Electrical Engineering, National Research Council of Canada, Ottawa, Ont., Canada K1A 0R8.
fDate :
5/1/1985 12:00:00 AM
Abstract :
To estimate the position of a subpicture P1 (with unknown angular misaligment) in a contour map P2, a method based on Fourier descriptors of multidirectional gradient codes is suggested. It is assumed that P2 is characterized by a set of magnitudes at equally spaceddiscrete points over a rectangular area; and P1 is described by a set of magnitudes at discrete points on directional axes emanated from a point with magnitude c*. Using the measurements of P1, the multidirectional gradient or successive-gradient codes and their Fourier descriptors are generated. A contour map for P2 having c* as one of the isopleth values is then obtained. For each point on all c*-isopleths, a two-level classifier, utilizing information derived from the Fourier descriptors and the phase correlation function, is used to estimate the possible location of P1 in P2. Simulation has indicated that in many cases the angular misalignment and the position of P1 with respect to P2 can be determined.
Keywords :
Biomedical measurements; Character recognition; Councils; Filtering; Image registration; Kalman filters; Layout; Matched filters; Phase estimation; Probes; Angular misalignment estimation; Fourier descriptors; continuous gradient function; contour-map processing; image registration; multidirectional gradient codes; phase correlation function;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1985.4767662