Abstract
We discuss the problem of how to determine whether two patterns are identical up to some rotation. Much work on this topic in machine vision relies on first-order correlation procedures to determine the magnitudes of the angular-frequency components in the patterns. Because phase information at each frequency is ignored, such strategies identify patterns that are not related by a rotation. How can we capture this phase information, which is needed for fully rotation-invariant recognition? Generalized autocorrelation functions1 provide increasingly more information about relative phases at each angular frequency as the order of the generalized autocorrelation is increased. We examine the conditions on image patterns under which nth-order autocorrelation functions can be used for fully rotation-invariant recognition. The results show that for many applications fully rotation-invariant recognition can be achieved only through generalized correlation procedures that are computationally intractable. We show that this difficulty in capturing the rotation-invariant aspects of patterns extends to many groups of transformations of interest in vision research that have as a subgroup the group SO(2) of rotations.
© 1990 Optical Society of America
PDF ArticleMore Like This
Henry Stark and Ron Wu
ThD3 Machine Vision (MV) 1985
Henri H. Arsenault
FF1 OSA Annual Meeting (FIO) 1988
Thomas A. Isberg and G. Michael Morris
TUR4 OSA Annual Meeting (FIO) 1985