Media.Player

Improved Spoof Detection for Facial Recognition

Detailed Technology Description

Executive Summary As biometrics become more prevalent in our technology, the more important security and detection of illegitimate access attempts becomes. This technology improves the spoof detection capability of facial recognition technology, providing not only identification and rejection of a spoof face, but provide its rationale for rejection as well. Description of Technology This MSU-developed technology is capable of distinguishing a spoof face from a live face when presented with a print, replay, or mask attack. Using a novel neural network architecture and highly specialized training database, this software is not only capable of recognizing a presentation attack, but also provides intelligent feedback to the user. This “explainable artificial intelligence” feature is possible due to classification of attacks and the software’s ability to recognize spoof patterns. Key BenefitsClassifies spoof vs. real faceReasoning for rejection statedLearns spoof patternsTrained with diverse databaseAllows for better performance across various races, genders, etc. ApplicationsFacial recognition softwareBiometric lockSurveillance systems Patent Status:   Patent pending Licensing Rights Available Non-exclusive rights available Inventors: Xiaoming Liu,Yaojie Liu, Amin Jourabloo Tech ID: TEC2018-0077

*Abstract

None

*Principal Investigator

Name: Xiaoming Liu, Assistant Professor

Department: Computer Science & Engineering

Name: Yaojie Liu, Student

Department: Computer Science and Engineering

Name: Amin Jourabloo, Doctoral Student

Department: Computer Science & Engineering

Country/Region

USA