Face Recognition Vendor Test (FRVT) Part 4A: MORPH - Utility of 1:N Face Recognition Algorithms for Morph Detection
Mei Lee Ngan, Patrick J. Grother, Kayee Hanaoka
This report is a part of a series of studies on the topic of face morphing, its relevance and implications as a vulnerability to automated face recognition, and methods to aid in detecting morphs. Expanding on concepts introduced in a study conducted by the Dutch Vehicle Authority, this report presents a methodology and quantitative results on the use of automated one-to-many (1:N) face recognition algorithms as a mechanism to potentially detect the presence of morphs. This report is intended to inform end-users and identity credential issuance entities, especially those that accept user-submitted photos, in understanding how a 1:N search against a centralized database might be used to flag suspicious activity related to face morphing. Our proposed methodology analyzes the rank 1 and rank 2 scores that are returned on candidate lists from searching morph and bona fide photos against both consolidated and unconsolidated galleries of 1.6 million unique subjects under new enrollment and renewal scenarios. Morph classifiers are trained using the rank 1 and 2 score pairs from a number of modern 1:N face recognition algorithms to quantify the utility of these scores in detecting morphs.
, Grother, P.
and Hanaoka, K.
Face Recognition Vendor Test (FRVT) Part 4A: MORPH - Utility of 1:N Face Recognition Algorithms for Morph Detection, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.8430, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=934958
(Accessed September 26, 2023)