NEURAL NETWORK ANALYSIS OF IMAGES FOR NON-DESTRUCTIVE EVALUATION
John S. Sadowsky, Isaac N. Bankman, Vincent G. Sigillito · 2005
This paper reports an effort to develop a neural network-based system that is capable of analyzing images for the presence of particular features. In particular, the system would automatically analyze X-ray images as part of a non-destructive evaluation (NDE) function. Of particular interest is the development of neural network-based systems that can easily and inexpensively be retrained when design changes are made in parts to be inspected. Backpropagation networks with one hidden layer, based on classification and image compression concepts, were designed and tested with X-rays of Army M764 fuzes.