15 May 2019 in IEEE Access
Iris segmentation algorithms are of great significance in complete iris recognition systems and directly affect the iris verification and recognition results. However, conventional iris segmentation algorithms have poor adaptability and are not sufficiently robust when applied to noisy iris databases captured under unconstrained conditions. Additionally, there are currently no large iris databases; thus, iris segmentation algorithms cannot maximize the benefits of convolutional neural networks (CNNs). The main work of this paper is as follows: first, we propose an architecture based on CNNs combined with dense blocks for iris segmentation, referred to as a dense-fully convolutional network (DFCN), and adopt some popular optimizer methods, such as batch normalization (BN) and dropout. Second, because the public ground-truth masks of the CASIA-Interval-v4 and IITD iris databases do not include the labeled eyelash regions, we label these regions that occlude the iris regions using the Labelme software package. Finally, the promising results of experiments based on the CASIA-Interval-v4, IITD and UBIRIS.V2 iris databases captured under different conditions reveal that the iris segmentation network proposed in this paper outperforms all of the conventional and most of the CNN-based iris segmentation algorithms with which we compared our algorithm’s results in terms of various metrics, including the accuracy, precision, recall, f1 score, and nice1 and nice2 error scores, reflecting the robustness of our proposed network.
19 June 2019 in IEEE Access
30 August 2021 in International Journal of Intelligent Systems
1 May 2021 in Journal of Electronic Imaging
<!-- *** Custom HTML *** --> With the rapid development of deep learning, iris recognition methods based on deep learning are constantly being proposed. These methods generally consist of iris segmentation and normalization to more accurately locate iris regions and reduce the impact of iris feature changes caused by pupil expansion. We propose a non-segmentation (NS) iris recognition framework based on a deep learning classification model, which directly takes a raw image as input for feature extraction and recognition without performing iris segmentation and normalization. This method outperforms other methods. We proposed a non-segmentation network (NSNet). NSNet is a convolutional neural network (CNN) based on an attention mechanism that enhances the robustness and accuracy of the network by reusing features and assigning channel attention values. In addition, while ensuring the advanced performance of the network, it uses only 31 convolutional layers to complete iris feature extraction and recognition tasks in the NS iris recognition framework. Since the deep learning classification model cannot recognize that the category of an image is an untrained image category, we proposed a dual-threshold iris framework. In the proposed framework, all untrained image categories are classified as impostor classes, and the first threshold set in the proposed framework can effectively prevent impostors and eliminate inferior images. The proposed framework is suitable for the pursuit of more accurate, more robust, and safer private iris recognition scenarios. We conduct experiments with uniform parameter settings on four publicly available databases and shows that even in the challenging situation where a raw image is used as the input image, the proposed method is still the most advanced algorithm. Moreover, a series of ablation experiments were conducted to further confirm that the proposed framework has a higher accuracy, robustness, and generalizability through verification and discussion.
15 May 2019 in Journal of Electronic Imaging
Iris recognition (IR) is widely adopted for human identification in the biometric fields. However, results using handcrafted features designed with the domain knowledge are obtained by conventional IR algorithms which are complex. Convolutional neural networks (convnets) have been proved to be robust with superior learning capability in many computer vision fields. The deep convnets perform better than shallower convnets. However, training the deep convnets for IR is difficult. IrisConvDeeper, an adaptive architecture based on convnets combining Softmax classifier that is used to alleviate the problems of training deep convnets for IR, is proposed. In addition, a better performance is obtained. Furthermore, a shallower architecture termed as IrisConvShallower is designed for comparison. IrisConvDeeper consists of structures called dense block and has 12 or 14 convolutional layers. Meanwhile, IrisConvShallower consists of six or seven standard convolutional layers. The performance of the proposed architectures is tested on two public iris databases, which are collected under different conditions: CASIA-Iris-V3 and IITD iris image databases. The experimental results demonstrate that the proposed IrisConvDeeper outperforms most of state-of-the-art approaches in terms of correct recognition rate, except some approaches that adopted specific methods and identified fewer subjects compared with our methods.
1 November 2021 in Journal of Electronic Imaging
With the broad application of iris recognition systems, iris images acquired under cross-sensor and cross-spectrum conditions are increasingly common. Differences in the information stored in these images place high requirements for accuracy and robustness on cross-domain iris recognition algorithms, and current algorithms have not performed well in cross-domain iris recognition. Hence, we propose a dense squeeze and excitation network (DenseSENet) to extract common features in cross-domain iris images and use real-valued features for cross-domain matching. DenseSENet is a deep convolutional neural network based on an attention mechanism. It uses the batch normalization-rectified linear unit-Conv1 × 1 structure to increase the nonlinearity of the network and repeatedly uses features through dense connections to effectively prevent overfitting. The proposed dense squeeze and excitation structure extracts more accurate and stable features by learning the relations between channels and assigning corresponding attention values. The structure of global average pooling-fully connected-softmax is utilized to obtain compact and normalized real-valued feature templates to effectively reduce the size of the iris template. The proposed cross-domain iris recognition framework based on DenseSENet is end-to-end, which transforms the cross-domain matching problem to a many-to-one classification problem. Experiments are conducted on publicly available cross-sensor and cross-spectral iris databases. The results show that the proposed real-valued feature matching based on DenseSENet has better matching accuracy and robustness than the state-of-art cross-domain matching algorithm on two publicly available cross-sensor and cross-spectral iris databases.