The iris recognition is mainly aimed at iris matching, and everyone has a different iris. In this paper, design an efficient Convolutional Neural Network for iris recognition. First need to preprocess the iris image and the iris region of the eye is extracted. And then, divide the iris area into eight rectangular regions, those sub-regions are put into the designed model, which can extract the iris abstract features and identify the iris. Finally, train the model by collecting large amounts of data and that the correctness of the model can reach about 99.0%, which can meet the requirement of iris recognition effectively.
展开▼
