A Deep Learning Iris Recognition Method Based on Capsule Network Architecture

Iris recognition is one of the most representative identification technologies in biometric recognition, which is widely used in various fields. Recently, many deep learning methods have been used in biometric recognition, owing to their advantages such as automatic learning, high accuracy, and strong generalization ability. The deep convolutional neural network (CNN) is the mainstream method of image processing widely used in many domains, but it has poor anti-noise capacity in image classification and is easily affected by slight disturbances. CNN also needs a large number of samples for training. The recent capsule network not only has high recognition accuracy in classification tasks but can also learn part-whole relationships, increasing the robustness of the model. Furthermore, it can be trained using a small number of samples. In this paper, we propose a deep learning method based on the capsule network architecture in iris recognition. The structure detail of the network is adjusted, and we provide a modified routing algorithm based on the dynamic routing between two capsule layers to make this technique adapt to iris recognition. Migration learning makes the deep learning method available even when the number of samples is limited. Therefore, three state-of-the-art pretrained models, VGG16, InceptionV3, and ResNet50, are introduced. We divide the three networks into a series of subnetwork structures according to the number of their major constituent blocks. They are used as the convolutional part to extract primary features, instead of a single convolutional layer in the capsule network. Our experiments are conducted on three iris datasets, JluIrisV3.1, JluIrisV4, and CASIA-V4 Lamp, to analyze the performance of different network structures. We also test the proposed networks in simulated strong and weak light environments, showing that the networks with capsule architecture are more stable than those without.