Pattern recognition with parallel associative memoryAn examination is conducted of the feasibility of searching targets in aerial photographs by means of a parallel associative memory (PAM) that is based on the nearest-neighbor algorithm; the Hamming distance is used as a measure of closeness, in order to discriminate patterns. Attention has been given to targets typically used for ground-control points. The method developed sorts out approximate target positions where precise localizations are needed, in the course of the data-acquisition process. The majority of control points in different images were correctly identified.
Document ID
19920069016
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Toth, Charles K. (NASA Headquarters Washington, DC United States)
Schenk, Toni (Ohio State University Columbus, United States)