Although the impact of natural movement/sway while standing still during the capture of a 3D face model for biometric applications has previously been believed to have a negligible impact on biometric performance, utilizing a newly captured dataset, this paper demonstrates a significant negative impact of standing.
A 0.5 improvement in d' (test of correct/incorrect match distribution separation) per 3D face region and noticeable improvement to match distributions are shown to result from eliminating movement during the scanning process. By comparing these match distributions to those in the FRGC dataset, this paper presents an argument for improving the accuracy of 3D face models by eliminating motion during the capture process. (Publisher abstract provided)
Downloads
Similar Publications
- Biometric Classifier Update Using Online Learning: A Case Study in Near Infrared Face Verification
- ChatGPTing Securely: Using Machine Learning to Automate Writing Rape Reports, Closed Source Large Language Models
- Measuring the Direct and Spillover Effects of Body-Worn Cameras on the Civility of Police–Citizen Encounters and Police Work Activities