No abstract

Venipuncture is a common process in medical treatment. In the fight against pandemic like COVID-19, it is often very difficult for medical staff to carry out venipuncture accurately, since the staff have to wear safety glasses and surgical gloves. In this work, we designed an embedded system which implements deep learning algorithm to localize veins from color skin images. The proposed method consists of a fully convolutional neural network (CNN) as encoder and feature extractor, a dilated convolution module, and a transposed convolution module as decoder. A synchronized RGB/Near Infrared (NIR) image database was constructed to provide the mapping information between the two image fields. A combined loss function which includes a per-pixel loss and a perceptual loss was presented to optimize the network parameters. To make the model adaptive to different images, a histogram specification scheme was adopted to transform the color style of an image. The model was then implemented on a NVIDIA Jetson TX2 development kit. Comprehensive experiments were conducted on different databases to evaluate the proposed method and the embedded system. Experimental results showed that the system has satisfactory performance and a promising perspective in daily medical treatment. INDEX TERMS vein localization, convolutional neural network, NVIDIA Jetson TX2 Chaoying Tang (S'11-M'15) received her B.Eng. and M.Eng. degrees, both in Automation, from Nanjing University of Aeronautics and Astronautics, China. She got her Ph.D. degree from the School of

Biometrics are the among most popular authentication methods due to their advantages over traditional methods, such as higher security, better accuracy and more convenience. The recent COVID‐19 pandemic has led to the wide use of face masks, which greatly affects the traditional face recognition technology. The pandemic has also increased the focus on hygienic and contactless identity verification methods. The forearm is a new biometric that contains discriminative information. In this paper, we proposed a multimodal recognition method that combines the veins and geometry of a forearm. Five features are extracted from a forearm Near‐Infrared (Near‐Infrared) image: SURF, local line structures, global graph representations, forearm width feature and forearm boundary feature. These features are matched individually and then fused at the score level based on the Improved Analytic Hierarchy Process‐entropy weight combination. Comprehensive experiments were carried out to evaluate the proposed recognition method and the fusion rule. The matching results showed that the proposed method can achieve a satisfactory performance.