Skip to main content

NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.

Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.

U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

A Methodology for Detecting Face Morphing Using One-To-Many Face Recognition Algorithms

Published Patent Application Number: US20250005912A1

Problem

(a) Subject A, (b) Subject ( A+B), and (c) Subject B

Face morphing (two or more facial images are combined) is a known vulnerability to automated facial recognition. While face morphing has been used for benign entertainment purposes, it can be used for nefarious purposes such as identity fraud.

Invention

A morph detection method that uses one-to-many (1 :N) face recognition algorithms to detect the presence of face morphing under certain scenarios.

Potential Commercial Applications

  • Detection of morphed images for organizations that accept user-submitted application photos during renewal processes.
  • Adaptable methodology for eGate systems that can connect to backend databases.

Competitive Advantage

  • User Convenience: Reduced false detection rates when compared to other conventional morph detection algorithms.
  • Cost-Efficient: Can leverage existing one-to-many face recognition infrastructure by adapting this methodology.
Created June 18, 2025, Updated September 9, 2025
Was this page helpful?