The fundamental problems of automatic target recognition (ATR) are discussed. A new approach to ATR is suggested that includes: a new method of scoring ATR performance, a new concept of artificial images, a new method called probing for extracting target signature knowledge from image experts, and suggestions for coping with the problem of insufficient test data and algorithm obsolescence
Published in:
Aerospace and Electronic Systems, IEEE Transactions on
(Volume:28
,
Issue:
1
)
Date of Publication: Jan 1992