Evaluating and Enhancing Face Anti-Spoofing Algorithms for Light Makeup: A General Detection Approach

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 24; p. 8075
• Main Authors: Lai, Zhimao, Guo, Yang, Hu, Yongjian, Su, Wenkang, Feng, Renhai
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.12.2024
• Subjects: Algorithms; Automated Facial Recognition - methods; Biometry; Comparative analysis; Cosmetics; Databases, Factual; Deep learning; deep neural network; Face; face anti-spoofing; Fraud; general detection; Holidays & special occasions; Humans; Image Processing, Computer-Assisted - methods; Light; makeup transfer; metric learning; Supervision; China; face anti-spoofing; metric learning; general detection; deep neural network; makeup transfer
• DOI: 10.3390/s24248075
• ISSN: 1424-8220

Makeup modifies facial textures and colors, impacting the precision of face anti-spoofing systems. Many individuals opt for light makeup in their daily lives, which generally does not hinder face identity recognition. However, current research in face anti-spoofing often neglects the influence of light makeup on facial feature recognition, notably the absence of publicly accessible datasets featuring light makeup faces. If these instances are incorrectly flagged as fraudulent by face anti-spoofing systems, it could lead to user inconvenience. In response, we develop a face anti-spoofing database that includes light makeup faces and establishes a criterion for determining light makeup to select appropriate data. Building on this foundation, we assess multiple established face anti-spoofing algorithms using the newly created database. Our findings reveal that the majority of these algorithms experience a decrease in performance when faced with light makeup faces. Consequently, this paper introduces a general face anti-spoofing algorithm specifically designed for light makeup faces, which includes a makeup augmentation module, a batch channel normalization module, a backbone network updated via the Exponential Moving Average (EMA) method, an asymmetric virtual triplet loss module, and a nearest neighbor supervised contrastive module. The experimental outcomes confirm that the proposed algorithm exhibits superior detection capabilities when handling light makeup faces.