Head poses and grimaces: Challenges for automated face identification algorithms?

In today's biometric and commercial settings, state-of-the-art image processing relies solely on artificial intelligence and machine learning which provides a high level of accuracy. However, these principles are deeply rooted in abstract, complex "black-box systems". When applied to forensic image identification, concerns about transparency and accountability emerge. This study explores the impact of two challenging factors in automated facial identification: facial expressions and head poses. The sample comprised 3D faces with nine prototype expressions, collected from 41 participants (13 males, 28 females) of European descent aged 19.96 to 50.89 years. Pre-processing involved converting 3D models to 2D color images (256 x 256 px). Probes included a set of 9 images per individual with head poses varying by 5 degrees in both left-to-right (yaw) and up-and-down (pitch) directions for neutral expressions. A second set of 3,610 images per individual covered viewpoints in 5 degrees increments from -45 degrees to 45 degrees for head movements and different facial expressions, forming the targets. Pair-wise comparisons using ArcFace, a state-of-the-art face identification algorithm yielded 54,615,690 dissimilarity scores. Results indicate that minor head deviations in probes have minimal impact. However, the performance diminished as targets deviated from the frontal position. Right-to-left movements were less influential than up and down, with downward pitch showing less impact than upward movements. The lowest accuracy was for upward pitch at 45 degrees. Dissimilarity scores were consistently higher for males than for females across all studied factors. The performance particularly diverged in upward movements, starting at 15 degrees. Among tested facial expressions, happiness and contempt performed best, while disgust exhibited the lowest AUC values.