SYMPOSIUM MINISYMPOSIA

ABSTRACT

Neural networks are considered one of the best tools for the pattern recognition problem. In a typical application, an image is first pre-processed by some feature-extracting program, and thus significantly simplified, before it is shown to the network (either as a training or testing data). This procedure leads to a relatively small neural network (in terms of the number of input and internal nodes). We will present the results of investigating the preformance of various Neural Networks, available in the NeuroShell environment, applied to a simplified multifont recognition problem. Each of these networks has been applied to the letter image directly (without any initial pre-processing) and thus the size of the networks is relatively large.

Getting More Information

To obtain more information about the meeting send e-mail to: fscc98@pax.st.usm.edu.

Return to PAX
Return to USM

USM
inquire@delphi.st.usm.edu
Updated
http://pax.st.usm.edu