This report documents performance of one-to-many face identification algorithms, and compares it with that in 2010. Performance in this context refers recognition accuracy and computational resource usage as measured by executing those algorithms on massive sequestered datasets. These are: reasonable quality law enforcement mugshot images; poor quality webcam images collected in similar detention operations; and moderate quality visa application images. The mugshot and visa images are used to approximate performance obtainable using high quality ISO standardized images collected in passport, visa and driving license duplicate detection operations.
Citation: NIST Interagency/Internal Report (NISTIR) - 8009
NIST Pub Series: NIST Interagency/Internal Report (NISTIR)
Pub Type: NIST Pubs
biometrics, face recognition, identification, forensics, pattern recognition