Visual entity identification: a neural network approach
C. Riley, P. Work, R. Miller · 2002
Summary form only given. An increasingly large volume of image data requires automatic analysis to detect and classify entities. Neural networks are a tool that can be used to process these images. Standard back propagation is being used to train a neural network to identify multiple entities from images. A study is being conducted to demonstrate that the application of neural networks to entity identification is feasible.>