Four Principles of Explainable AI as Applied to Biometrics and Facial Forensic Algorithms
This work addresses the need for explainable AI in biometrics and facial forensic algorithms to meet societal norms, but it is incremental as it adapts existing principles rather than introducing new methods.
The paper tackles the problem of trust in AI systems by adapting explainable AI principles to face recognition and biometrics, presenting four principles illustrated through case studies that highlight challenges in developing algorithms capable of producing explanations.
Traditionally, researchers in automatic face recognition and biometric technologies have focused on developing accurate algorithms. With this technology being integrated into operational systems, engineers and scientists are being asked, do these systems meet societal norms? The origin of this line of inquiry is `trust' of artificial intelligence (AI) systems. In this paper, we concentrate on adapting explainable AI to face recognition and biometrics, and we present four principles of explainable AI to face recognition and biometrics. The principles are illustrated by $\it{four}$ case studies, which show the challenges and issues in developing algorithms that can produce explanations.