Real-time iris recognition system using a rotation spreading neural network

摘要

We previously proposed a rotation spreading neural network. The characteristics of this neural net is to spread the information of axis orientation of the object on surrounding space by spreading weight that has similar tuning characteristics to axis orientation neurons in the parietal cortex. This neural net is suitable for the shape and orientation recognition of a concentric circular pattern, because it uses the polar conversion. Previously, the validity of this neural net for learning and recollection of human faces had been shown by off-line processing. In the present study, we used iris images instead of face images for input patterns of the neural network. We tried real-time individual identification by the iris patterns. In the recognition experiment, the rotation spreading neural network was able to recognize orientation and shape of the iris images of learned persons simultaneously. In results, we suggested the iris recognition system application of the rotation spreading neural network.