Automatic ground control point recognition with parallel associative memoryThe basic principle of the associative memory is to match the unknown input pattern against a stored training set, and responding with the 'closest match' and the corresponding label. Generally, an associative memory system requires two preparatory steps: selecting attributes of the pattern class, and training the system by associating patterns with labels. Experimental results gained from using Parallel Associative Memory are presented. The primary concern is an automatic search for ground control points in aerial photographs. Synthetic patterns are tested followed by real data. The results are encouraging as a relatively high level of correct matches is reached.
Document ID
19920031266
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Al-Tahir, Raid (Ohio State Univ. Columbus, OH, United States)
Toth, Charles K. (Ohio State Univ. Columbus, OH, United States)
Schenck, Anton F. (Ohio State University Columbus, United States)