Face Authentication With Makeup Changes

• Published in: IEEE transactions on circuits and systems for video technology Vol. 24; no. 5; pp. 814 - 825
• Main Authors: Guo, Guodong, Wen, Lingyun, Yan, Shuicheng
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.05.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Authentication; Biometrics; Correlation; Cosmetics; Cryptography; Detection, estimation, filtering, equalization, prediction; discriminative; Exact sciences and technology; Face; Face recognition; Face verification; Feature extraction; Image color analysis; Image processing; Information, signal and communications theory; makeup detection; Mapping; partial least squares; patch selection; Pattern recognition; Robustness; Signal and communications theory; Signal processing; Signal, noise; Skin; Surface layer; Telecommunications and information theory; Texture; Correlation; makeup detection; discriminative; face verification; partial least squares; patch selection; cosmetics; Biometrics; Performance evaluation; Discriminant analysis; Face recognition; Image processing; Mapping; Pattern recognition; Timbre; Texture; Accuracy; Authentication; Database; Signal processing; Selection criterion; Feature extraction; Automatic recognition; Partial least squares
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2013.2280076

Recent studies have shown that facial cosmetics have an impact on face recognition. To develop a face recognition system that is robust to facial makeup, we propose performing correlation mapping between makeup and nonmakeup faces on features extracted from local patches. Three methods are explored to learn the correlations. We also study the problem of makeup detection. Four categories of features are proposed to characterize cosmetics, including skin color tone, skin smoothness, texture, and highlight. A patch selection scheme and discriminative mapping are presented to enhance the performance of makeup detection. A complete system is then developed for face verification utilizing the makeup detection result. Experimental results show that our system is robust to cosmetics in face authentication. An accuracy of about 80.0% can be achieved on a database of about 500 pairs of makeup and nonmakeup face images.