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. INDEX TERMS Iris recognition, deep learning, capsule network, transfer learning.

Aircraft detection in Synthetic Aperture Radar (SAR) images is still a challenging research task because of the insufficient public data, the difficulty of multi-scale target detection, and the complexity of background interference. In this paper, we construct a public SAR Aircraft Detection Dataset (SADD) with complex background and interference objects to facilitate the research in SAR aircraft detection. Then, we propose the Scale Expansion and Feature Enhancement Pyramid Network (SEFEPNet) as the SADD baseline. It uses a four-scale fusion method to combine the shallow position information with the deep semantic information, effectively adapting to the multiscale target detection in SAR images, significantly improving the detection effect of small targets. The Feature Enhancement Pyramid (FEP) structure is connected behind the backbone network to weaken the background texture and highlight the target to achieve feature enhancement, improving the ability to extract target features in complex backgrounds. Finally, to further improve the detection performance of the small-scale SAR aircraft dataset, we propose a domain adaptive transfer learning method. Experiments on SADD show that this method can significantly improve the recall rate and F1 score. At the same time, we find that the transfer effect of using homologous but different types of targets as the source domain is better than those of heterologous but same types of targets in SAR aircraft detection, which is instructive for future research.

Graphical User Interface (GUI) is ubiquitous in almost all modern desktop software, mobile applications, and online websites. A good GUI design is crucial to the success of the software in the market, but designing a good GUI which requires much innovation and creativity is difficult even to well-trained designers. Besides, the requirement of the rapid development of GUI design also aggravates designers' working load. So, the availability of various automated generated GUIs can help enhance the design personalization and specialization as they can cater to the taste of different designers. To assist designers, we develop a model GUIGAN to automatically generate GUI designs. Different from conventional image generation models based on image pixels, our GUIGAN is to reuse GUI components collected from existing mobile app GUIs for composing a new design that is similar to natural-language generation. Our GUIGAN is based on SeqGAN by modeling the GUI component style compatibility and GUI structure. The evaluation demonstrates that our model significantly outperforms the best of the baseline methods by 30.77% in Frechet Inception distance (FID) and 12.35% in 1-Nearest Neighbor Accuracy (1-NNA). Through a pilot user study, we provide initial evidence of the usefulness of our approach for generating acceptable brand new GUI designs.

No abstract