Pixel-Level Face Image Quality Assessment for Explainable Face Recognition
This work addresses the need for explainable face recognition systems, which are increasingly used in daily life, by providing a method to enhance interpretability, though it is incremental as it builds on existing face recognition networks.
The paper tackles the problem of making face recognition systems more interpretable by introducing pixel-level face image quality assessment, which determines the utility of individual pixels for recognition, and demonstrates meaningful results in experiments with real and artificial disturbances.
An essential factor to achieve high performance in face recognition systems is the quality of its samples. Since these systems are involved in daily life there is a strong need of making face recognition processes understandable for humans. In this work, we introduce the concept of pixel-level face image quality that determines the utility of pixels in a face image for recognition. We propose a training-free approach to assess the pixel-level qualities of a face image given an arbitrary face recognition network. To achieve this, a model-specific quality value of the input image is estimated and used to build a sample-specific quality regression model. Based on this model, quality-based gradients are back-propagated and converted into pixel-level quality estimates. In the experiments, we qualitatively and quantitatively investigated the meaningfulness of our proposed pixel-level qualities based on real and artificial disturbances and by comparing the explanation maps on faces incompliant with the ICAO standards. In all scenarios, the results demonstrate that the proposed solution produces meaningful pixel-level qualities enhancing the interpretability of the complete face image quality. The code is publicly available