ABSTRACT
Traditional fingerprint authentication requires the acquisition of data through touch-based specialized sensors. However, due to many hygienic concerns including the global spread of the COVID virus through contact with a surface has led to an increased interest in contactless fingerprint image acquisition methods. Matching fingerprints acquired using contactless imaging against contact-based images brings up the problem of performing cross modal fingerprint matching for identity verification. In this paper, we propose a cost-effective, highly accurate and secure end-to-end contactless fingerprint recognition solution. The proposed framework first segments the finger region from an image scan of the hand using a mobile phone camera. For this purpose, we developed a cross-platform mobile application for fingerprint enrollment, verification, and authentication keeping security, robustness, and accessibility in mind. The segmented finger images go through fingerprint enhancement to highlight discriminative ridge-based features. A novel deep convolutional network is proposed to learn a representation from the enhanced images based on the optimization of various losses. The proposed algorithms for each stage are evaluated on multiple publicly available contactless databases. Our matching accuracy and the associated security employed in the system establishes the strength of the proposed solution framework.
ABSTRACT
Objective: During the COVID-19 pandemic, scientific congresses have moved from in-person to a fully virtual setting. We evaluated whether QR code metrics may provide insight into the reach of congress poster presentations in the virtual vs in-person setting, specifically posters pertaining to rare diseases in Hematology, Immunology, and Transplantation. Research design and methods: QR download metrics (via browser, email or SMS) for global Takeda-sponsored posters at select scientific congresses were obtained from the Takeda congress website. QR metrics were evaluated for two time periods: (1) pre- COVID period (January 2019-February 2020) and (2) COVID period (March-December 2020). The transition to the virtual setting during the COVID-19 pandemic was evaluated and QR metrics for each congress that switched from the in-person to virtual setting compared. Results: Database searching identified 193 posters at 54 in-person congresses (all of which were prior to 28 February 2020) and 67 posters at 27 virtual congresses (all after 1 March 2020). QR data were available for both the 2019 in-person and the 2020 virtual format for 17 congresses: posters presented in-person generated on average 2.4-fold greater QR code downloads (805 downloads/ 78 posters;mean 10.3 per poster) than virtual posters (222/52;mean 4.3 per poster). Conclusions: Our findings provide insights into the current complex scientific communication environment, where congresses in 2020 have switched to a virtual setting or been cancelled/ postponed, impacting the reach to audience. As virtual scientific congresses have become the norm during the COVID-19 pandemic, QR codes are one tool that may provide a better understanding of the reach of poster presentations.