Pattern-recognition problems for which patterns cannot be recognized directly but by their attitudes and/or behaviors is addressed. To analyze these attitudes, pattern signatures are generated from picture sequences. Two complementary signature synthesis algorithms are presented. The architecture is made up of two cascaded correlators. The first is used to create the signatures and the second to classify them. We focus our analysis on the case of optical implementations. Illustrations are given in the case of face recognition by attitudes (multisensor in the optronic imaging range) and moving-target recognition by behavior (in the radar imaging range).
© 2000 Optical Society of AmericaFull Article | PDF Article