FIAPR BMVA Distinguished Fellow 2015
School of Electronics and Computer Science University of Southampton UK
http://users.ecs.soton.ac.uk/msn/Link opens in a new window
Keynote talk: A Question of Evidence: gait, soft and ear biometrics and forensics
Abstract: There is considerable interest in the use of biometrics as evidence in court procedures. This can replace the opinion of an expert with evidence produced using large databases together with estimates of the confidence in that evidence. This implies that the evidence is produced in an automated fashion with an explainable chain of reasoning and is relatively free from bias. Evidence can be summarised using conventional inter- and intra-class analysis, or by using a likelihood ratio. This talk will present the background to using biometrics in forensics, and cover the main points in its deployment in the variety of international court systems. The talk will concentrate in particular on the use of gait for evidence as this has been deployed in international prosecutions. The talk will also describe the use of ears for evidence and soft biometrics for recognition, summarise the stock of other techniques that have been used or prepared for biometric-based evidence, and consider the nature of evidence in hand-crafted and deep learning approaches. We shall conclude with considerations for future development together with suggestions for generating biometric evidence.
Mark S. Nixon is a Professor in the Vision, Learning and Control research group in the School of Electronics and Computer Science at the University of Southampton, UK. He was previously the President of the IEEE Biometrics Council and Vice Chair IEEE PSPB. He is a Fellow of the IAPR (for services to biometrics and computer vision) and the Distinguished Fellow of the BMVA 2015. His research interests are in image processing and computer vision and his team develops new techniques for static and moving shape extraction applied in medical image and behaviour analysis. He and his team were early workers in automatic face recognition, came to pioneer automatic gait recognition, helped to start ear biometrics and later soft biometrics for human identification. His books include Feature Extraction and Image Processing for Computer Vision (4th Ed. Academic Press 2019), Human ID Based on Gait (Springer 2005) and Doh! Fourier (World Scientific 2022). He has been chair/program co-chair for many conferences, especially biometrics ones, and given many invited talks.
Chair of the IEEE Information Forensics and Security Technical Committee - Term 2021-2022
University Federico II of Naples, Italy
Keynote talk: Towards generalization in Deepfake detection
Abstract: In recent years there have been astonishing advances in AI-based synthetic media generation. Thanks to deep learning-based approaches it is now possible to generate data with a high level of realism. While this opens up new opportunities for the entertainment industry, it simultaneously undermines the reliability of multimedia content and supports the spread of false or manipulated information, such as the well-known Deepfakes. In this context, it is important to develop automated tools to detect manipulated media in a reliable and timely manner. This talk will describe the most effective deep learning-based approaches for detecting deepfakes, with a focus on those that enable domain generalization. The results will be presented on challenging datasets with reference to realistic scenarios, such as the dissemination of manipulated images and videos on social networks.
Dr. Luisa Verdoliva is a Professor at the University Federico II of Naples, Italy, where she leads the Multimedia Forensics Lab. In 2018 she has been visiting professor at Friedrich-Alexander-University and in 2019-2020 she has been visiting scientist at Google AI in San Francisco. Her main contributions are in the area of multimedia forensics. She has published over 130 academic publications, including 50 journal papers. She has been technical Chair of the 2019 IEEE Workshop in Information Forensics and Security, general co-Chair of the 2019 ACM Workshop on Information Hiding and Multimedia Security and technical Chair of this same Workshop in 2021. She has been on the Editorial Board of IEEE Transactions on Information Forensics and Security and is currently Senior Associate Editor of IEEE Signal Processing Letters and Deputy EiC of IEEE Transactions on Information Forensics and Security. Dr. Verdoliva was the Chair of the IEEE Information Forensics and Security Technical Committee for the period 2021-2022. She is the recipient of the 2018 Google Faculty Research Award and a TUM-IAS Hans Fischer Senior Fellowship. She is IEEE Fellow.