This paper presents a new face identification system based on graph matching technique on SIFT features extracted from face images. Although SIFT features have been successfully used for general object detection and recognition, only recently they were applied to face recognition. This paper further investigates the performance of identification techniques based on Graph matching topology drawn on SIFT features which are invariant to rotation, scaling and translation. Face projections on images, represented by a graph, can be matched onto new images by maximizing a similarity function taking into account spatial distortions and the similarities of the local features. Two graph based matching techniques have been investigated to deal with false pair assignment and reducing the number of features to find the optimal feature set between database and query face SIFT features. The experimental results, performed on the BANCA database, demonstrate the effectiveness of the proposed system for automatic face identification.

Driven by technological advances in various fields (AI, 5G, VR, IoT, etc.) together with the emergence of digital twins technologies (HDT, HAL, BIM, etc.), the Metaverse has attracted growing attention from scientific and industrial communities. This interest is due to its potential impact on people lives in different sectors such as education or medicine. Specific solutions can also increase inclusiveness of people with disabilities that are an impediment to a fulfilled life. However, security and privacy concerns remain the main obstacles to its development. Particularly, the data involved in the Metaverse can be comprehensive with enough granularity to build a highly detailed digital copy of the real world, including a Human Digital Twin of a person. Existing security countermeasures are largely ineffective and lack adaptability to the specific needs of Metaverse applications. Furthermore, the virtual worlds in a large-scale Metaverse can be highly varied in terms of hardware implementation, communication interfaces, and software, which poses huge interoperability difficulties. This paper aims to analyse the risks and opportunities associated with adopting digital replicas of humans (HDTs) within the Metaverse and the challenges related to managing digital identities in this context. By examining the current technological landscape, we identify several open technological challenges that currently limit the adoption of HDTs and the Metaverse. Additionally, this paper explores a range of promising technologies and methodologies to assess their suitability within the Metaverse context. Finally, two example scenarios are presented in the Medical and Education fields.

Dementia represents a global public health concern, with the early detection of Alzheimer's disease, the most prevalent form of dementia, being of paramount importance. Given the limited availability of suitable biomarkers, research has shown that early cognitive impairment can be identified through patients' spoken language. This paper presents a multi-modal system for automatic Alzheimer's disease detection using speech. The system has been trained on spoken recordings of healthy individuals and Alzheimer's patients describing an image, a task requiring linguistic and cognitive skills. Built on fine-tuned advanced Large Language Models, audio feature extractors, and classifiers, the system, after an extensive comparison of single and multi-modal architectures, achieves optimal results with the combination of Mistral-7B, VGGish, and Support Vector Classifier, outperforming previous methods on the ADReSSo 2021 test set.

3D modeling and reconstruction are critical to creating immersive XR experiences, providing realistic virtual environments, objects, and interactions that increase user engagement and enable new forms of content manipulation. Today, 3D data can be easily captured using off-the-shelf, specialized headsets; very often, these tools provide real-time, albeit low-resolution, integration of continuously captured depth maps. This approach is generally suitable for basic AR and MR applications, where users can easily direct their attention to points of interest and benefit from a fully user-centric perspective. However, it proves to be less effective in more complex scenarios such as multi-user telepresence or telerobotics, where real-time transmission of local surroundings to remote users is essential. Two primary questions emerge: (i) what strategies are available for achieving real-time 3D reconstruction in such systems? and (ii) how can the effectiveness of real-time 3D reconstruction methods be assessed? This paper explores various approaches to the challenge of live 3D reconstruction from typical point cloud data. It first introduces some common data flow patterns that characterize virtual reality applications and shows that achieving high-speed data transmission and efficient data compression is critical to maintaining visual continuity and ensuring a satisfactory user experience. The paper thus introduces the concept of saliency-driven compression/reconstruction and compares it with alternative state-of-the-art approaches.

Today, more than ever before, technological progress is evolving rapidly, and in the absence of adequate regulatory frameworks, the big players in the digital market (the so-called Big Techs) are exploiting personal data (name, address, telephone numbers) and private data (political opinions, religious beliefs, financial information, or health status) in an uncontrolled manner. A crucial role in this scenario is played by the weakness of international regulatory frameworks due to the slow response time of legislators who are incapable, from a regulatory point of view, of keeping pace with technological evolution and responding to the new requirements coming from the social context, which is increasingly characterized by the pervasive presence of new technologies, such as smartphones and wearable devices. At the European level, the General Data Protection Regulation (GDPR) and the Regulation on Electronic Identification, Authentication and Trust Services (eIDAS) have marked a significant turning point in the regulatory landscape. However, the mechanisms proposed present clear security issues, particularly in light of emerging concepts such as digital identity. Moreover, despite the centrality of biometric issues within the European regulatory framework and the practical introduction of biometric data within electronic national identity (eID) cards, there are still no efforts to use biometric features for the identification and authentication of a person in a digital context. This paper clarifies and precisely defines the potential impact of biometric-based digital identity and hypothesizes its practical use for accessing network-based services and applications commonly used in daily life. Using the Italian eID card as a model, an authentication scheme leveraging biometric data is proposed, ensuring full compliance with GDPR and eIDAS regulations. The findings suggest that such a scheme can significantly improve the security and reliability of electronic identification systems, promoting broader adoption of eIDAS solutions.