Face recognition has become a key technology in our society, frequently used in multiple applications, while creating an impact in terms of privacy. As face recognition solutions based on artificial intelligence (AI) are becoming popular, it is critical to fully understand and explain how these technologies work in order to make them more effective and accepted by society. In this project, we focus on the analysis of the influencing factors relevant for the final decision of an AI-based face recognition system as an essential step to understand and improve the underlying processes involved. The scientific approach pursued in the project is designed in such a way that it will be applicable to other use cases such as object detection and pattern recognition tasks in a wider set of applications. Thanks to the interdisciplinary nature of the consortium, the outcomes of XAIface will affect many fields and can be summarized as follows: (i) develop clear legal guidelines on the use and design of AI-based face recognition following the privacy-by-design approach; (ii) disentangling demographic information (age, gender, ethnicity) from the overall face representation in order to understand the impact of such traits on face recognition but also to develop demographic-free face recognition; (iii) address fairness and non-discrimination issues by following the idea of de-biasing during the training; (iv) optimize the trade-off between interpretability and performance; (v) create tools that will allow assessment and measurement of performance and explanation of decisions of AI-based face recognition systems; (vi) analyse image coding impact to better understand how future AI-based coding solutions may be different from a recognition explainability point of view. The achieved results will feed into the implementation of an end-to-end face recognition system for studying the impact of the various system processes in terms of recognition performance and explainability. This will provide a use case study on how to perform explainability analysis with the tools provided by our project.

Face recognition has become a key technology in our society, frequently used in multiple applications, while creating an impact in terms of privacy. As face recognition solutions based on machine learning are becoming popular it is critical to fully understand and explain how these technologies work in order to make them more effective and accepted by society. In this project, we focus on face recognition technologies based on artificial intelligence and the analysis of the influencing factors relevant for the final decision as an essential step to understand and improve the underlying processes involved. The scientific approach pursued in the project is designed in such a way that it will be applicable to other use cases such as object detection and pattern recognition tasks in a wider set of applications. One of the original aspects of the proposed project is in its scientific approach which targets explaining how machine learning solutions reach effective face recognition by identifying and analyzing the influencing factors that play an important role in the performance of face recognition in the end-to-end workflow, and their impact on the system’s decisions. In fact, such performance largely depends on the acquisition, enhancement, compression, analysis and decision making processes adopted in the workflow of a face recognition solution. Machine learning is currently used in many of the stages of such a workflow and various factors such as the dataset used in the training process, the approach used for training itself, the architecture of machine learning, and the types of attacks and interferences are among influencing factors that contribute to the understanding and explainability of the complete system.