Future Work

Abstract

The current simulator reads in two isolevel images at a time - one for each training subject - therefore the other 3 pairs of images have to be sequentially processed before the system can reach a classification decision. It would be far more convenient to be able to read and process all four pairs simultaneously in a single command. This can be achieved with the appropriate modifications to the software, however there was insufficient time to effect these changes. In order to make the system run at a reasonable (near real-time) speed, faster multiprocessor machines with much more memory (to minimize disk paging) and CPUs optimized for floating point calculations would be needed.