Existence problem of optical correlation based pattern recognition

The existence problem of optical correlation based pattern recognition,namely its rangeof validity and its limitation,is discussed in this paper conjointly with the function approximationtheory of neural networks.The conclusion is that only if the sets to be recognized are linearlyseparable(which is rare)or the subsets,in which a segmental sample of the targets is involved,are linearly separable,can the classical 4f optical correlation system carry out the task of recogni-tion inerrably.The recognition principle of a joint transform correlator is the same as that of a 4fsystem,and so is its range of validities.Based on the demonstration of the existence problem ofoptical correlation based pattern recognition an evaluation on some important problems that werestudied in this field over the past 40 years is presented explicitly.