Subjective Evaluation of High Dynamic Range Imaging for Face Matching
Rossella Suma, Kurt Debattista, Derrick G. Watson, Elisabeth Blagrove, Alan G. Chalmers · IEEE Transactions on Emerging Topics in Computing · 2019
Human facial recognition in the context of surveillance, forensics and photo-ID verification is a task for which accuracy is critical. Quite often limitations in the overall quality of facial images reduces individuals’ ability in taking decisions regarding a person’s identity. To verify the suitability of advanced imaging techniques to improve individuals’ performance in face matching we investigate how High Dynamic Range (HDR) imaging compares with traditional low (or standard) dynamic range (LDR) imaging in a facial recognition task. An HDR face dataset with five different lighting conditions is created. Subsequently, this dataset is used in a controlled experiment ($N$= 40) to measure performance and accuracy of human participants when identifying faces in HDR versus LDR. Results demonstrate that face matching accuracy and reaction time are improved significantly by HDR imaging. This work demonstrates scope for realistic image reproduction and delivery in face matching tasks and suggests that security systems could benefit from the adoption of HDR imaging techniques.