Title :
2-D invariant object recognition using distributed associative memory
Author :
Wechsler, Harry ; Zimmerman, George Lee
Author_Institution :
Dept. of Comput. Sci., George Mason Univ., Fairfax, VA, USA
fDate :
11/1/1988 12:00:00 AM
Abstract :
Complex-log conformal mapping is combined with a distributed associative memory to create a system that recognizes objects regardless of changes in rotation or scale. Information recalled from the memorized database is used to classify an object, reconstruct the memorized version of the object, and estimate the magnitude of changes in scale or rotation. The system response is resistant to moderate amounts of noise and occlusion. Several experiments using real gray-scale images are presented to show the feasibility of the approach
Keywords :
computerised pattern recognition; content-addressable storage; 2-D invariant object recognition; complex log conformal mapping; computerized pattern recognition; database; distributed associative memory; gray-scale images; system response; Associative memory; Computer vision; Conformal mapping; Image databases; Image recognition; Image representation; Machine vision; Marine vehicles; Object recognition; Remote sensing;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
