Podcast: The future of facial recognition

For our new episode of "Fraunhofer Innovisions: Nachgeforscht" we spoke to Philipp Terhörst. Philipp conducts research into biometrics and facial recognition methods based on artificial intelligence and provides information about facial representations, hard and soft biometric data, their bias and privacy concerns.

Chat GPT, Midjourney or DALL-E – we currently associate artificial intelligence primarily with large language models and their everyday use. They can write texts that are almost indistinguishable from those produced by humans or generate detailed, realistic images and videos. AI algorithms are also used for facial recognition and biometrics, which is the subject of today's podcast. Our guest Philipp knows all about it.
Philipp Terhörst was a research assistant at the Fraunhofer Institute for Computer Graphics Research IGD in Darmstadt, where he also wrote his dissertation entitled "Mitigating Soft-Biometric Driven Bias and Privacy Concerns in Face Recognition", which won 2nd place in the Fraunhofer ICT Dissertation Award 2022.