Iris segmentation is an important step in the process of iris recognition. Iris images collected under non-cooperative conditions always contain various noise, which is a challenge for iris segmentation. Most U-Net-based methods have made great achievements in iris segmentation. However, this architecture lacks of focusing on target structures of varying shapes, and robustness in segmenting objects with significant shape variations. In this paper, we propose RAG-Net: an efficient iris segmentation method based on deep learning. In contrast to many previous convolutional neural network (CNN)-based iris segmentation methods, we adopted the attention gate (AG) mechanism and ResNet-50 in the U-Net architecture to improve iris segmentation accuracy, the AG module was included in the skip connection part of the RAG-Net architecture to further identify salient feature regions and prune feature responses, which preserve only the activations relevant to the required information, and the ResNet-50 module was used to improve the robustness of the segmentation performance. Using this model, efficient iris segmentation in a non-cooperative environment can be realized. The proposed method was trained and evaluated using the CASIA.v4-distance, CASIA.v4-thousand, UBIRIS.v2, and MICHE-I databases. From the view of the segmentation results, the proposed RAG-Net is one of effective architecture in iris segmentation methods.
Biometric recognition technology has been widely used in various fields of society. Iris recognition technology, as a stable and convenient biometric recognition technology, has been widely used in security applications. However, the iris images collected in the actual non-cooperative environment have various noises. Although mainstream iris recognition methods based on deep learning have achieved good recognition accuracy, the intention is to increase the complexity of the model. On the other hand, what the actual optical system collects is the original iris image that is not normalized. The mainstream iris recognition scheme based on deep learning does not consider the iris localization stage. In order to solve the above problems, this paper proposes an effective iris recognition scheme consisting of the iris localization and iris verification stages. For the iris localization stage, we used the parallel Hough circle to extract the inner circle of the iris and the Daugman algorithm to extract the outer circle of the iris, and for the iris verification stage, we developed a new lightweight convolutional neural network. The architecture consists of a deep residual network module and a residual pooling layer which is introduced to effectively improve the accuracy of iris verification. Iris localization experiments were conducted on 400 iris images collected under a non-cooperative environment. Compared with its processing time on a graphics processing unit with a central processing unit architecture, the experimental results revealed that the speed was increased by 26, 32, 36, and 21 times at 4 different iris datasets, respectively, and the effective iris localization accuracy is achieved. Furthermore, we chose four representative iris datasets collected under a non-cooperative environment for the iris verification experiments. The experimental results demonstrated that the network structure could achieve high-precision iris verification with fewer parameters, and the equal error rates are 1.08%, 1.01%, 1.71%, and 1.11% on 4 test databases, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.