ABSTRACT
Recent regulations to block the widespread transmission of COVID-19 disease among people impose the use of facial masks indoor and outdoor. Such restriction becomes critical in all those scenarios where access controls take benefit from biometric recognition systems. The occlusions due to the presence of a facial mask make a significant portion of human faces unavailable for feature extraction and analysis. This work explores the contribution of the solely periocular region of the face to achieve a robust recognition approach suitable for mobile devices. Rather than working on a static analysis of the facial features, like largely done by work on periocular recognition in the literature, the proposed study focuses the attention on the analysis of face dynamics so that the spatio-temporal features make the recogniser frame-independent and tolerant to user movements during the acquisition. To obtain a lightweight processing, which is compliant with limited computing power of mobile devices, the spatio-temporal representation of the periocular region has analysed and classified through Machine Learning approaches. The experimental discussion has been performed on a new dataset, Mobile Masked Face REcognition Database, specifically designed to analyse the periocular region dynamics in presence of facial masks. For a wider comparative analysis, a publicly available dataset called XM2VTS has been considered as well as Deep Learning solutions have been experimented to discuss the challenging aspects of the recognition problem. Moreover, a summary of the state-of-the-art on periocular recognition driven by COVID pandemic has been presented, showing how the research efforts in this field focused on recognition of still images. Experimental results show promising levels of performance as well as limitations of the proposed approach, creating the premises for future directions. Author
ABSTRACT
The study presents a part of the operational framework of the “Project for Infrastructure and Strategic Strengthening of the Somali National University”, funded by the Italian Agency for Development Cooperation. The project, coordinated by Politecnico di Milano, aims to reconstruct the Gahayr campus of the Somali National University of Mogadishu, which is today almost destroyed due to the civil war. The preliminary phase for reconstruction is a detailed survey of the buildings and the area over which the Campus will be re-built. In a normal situation, the team in charge of the survey would have gone on-site in Mogadishu;nevertheless, the risky local conditions and the Covid-19 pandemic made it impossible to have foreign personnel on-site. Consequently, the choice was to train a local team remotely, giving them the theoretical and practical instruments to face a complete 3D survey of the area and the buildings. Harsh times cannot stop works and activities that usually need the presence of the survey team on the field. Careful planning of the activities, the online staff training and the continuous sharing of the information permitted to get high quality 3D metric results quickly and to have at disposal all dimensional and qualitative valuable information for the project, usable in real-time by the designers and architects without going directly on the site.