6 April 1995 Rejection of unfamiliar patterns with multilayer neural networks
Author Affiliations +
Most of the pattern recognition applications of multilayer neural networks have been concerned with classification and not rejection of a given pattern. For example, in character recognition all alphabetical characters must be recognized as one of the 26 characters, as there is nothing to reject. However, in many situations, there is no guarantee that all the patterns that will be presented to the network would actually belong to one of the classes on which the network has been trained. In such cases, a useful network must be capable of rejection as well as classification. In this paper we propose a scheme to develop multilayer networks with rejection capabilities. The discriminating power of the proposed technique appears to be comparable to that of the human eye.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Behrooz Kamgar-Parsi, Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi, Behzad Kamgar-Parsi, } "Rejection of unfamiliar patterns with multilayer neural networks", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); doi: 10.1117/12.205153; https://doi.org/10.1117/12.205153

Back to Top