This research is directed towards providing a solution to a particular problem involving the manufacture of laminated composite materials. A critical problem in this labor intensive and expensive process is the inspection of ply edges to determine whether they have been placed within tolerance. A machine vision system to automate this inspection process has been developed in an earlier phase of this research. The current research effort seeks to improve the accuracy, adaptability and speed of this system by the use of neural network techniques. The proposed image processing system will use a highly regular architecture that integrates neural network modules in layers, thus significantly increasing the learning speeds for the neural networks.
