Distortion-insensitive correlation constellation detection
Charles Casey, Laurence G. Hassebrook, Eli Crane, Aaron Davidson · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2011
There are applications that require detection of multiple features which remain consistent in shape locally, but may change position with respect to one another globally. We refer to these feature sets as multi-feature constellations. We introduce a multi-level correlation filter design which uses composite feature detection filters, which on one level detect local features, and then on the next level detect constellations of these local feature responses. We demonstrate the constellation filter method with sign language recognition and fingerprint matching.