Graduate School and Research Center in Digital Sciences

Integrating facial makeup detection into multimodal biometric user verification system

Derman, Ekberjan; Galdi, Chiara; Dugelay, Jean-Luc

IWBF 2017, 5th International Workshop on Biometrics and Forensics, 4-5 April 2017, Coventry, UK

Multimodal biometric fusion is generally used for increasing the verification accuracy by combining two or more biometric traits. Fusion systems with predefined constant weight values for each biometry becomes much popular. Among biometrics, face modality is one of the most common traits that is used in such fusion system. However, face verification suffers from many challenging difficulties, one of which is facial makeup. Recently, it has been shown that the accuracy of face verification can be impacted by the presence of facial makeup. And as such, the verification result of a multimodal fusion system with constant weight value for each biometry can be degraded by facial cosmetics. In this work, we propose a method of integrating facial makeup detection into the fusion system to increase performance. In our investigated scenario, score level fusion of face, fingerprint and iris verification are performed, while the weight value of each trait changes dynamically according to the level of makeup classification of test facial image. So far, this is the first work taking into account the facial makeup within a multimodal biometric verification system. Experiments on 1600 different subjects reveal that our proposed method can help in increasing the overall performance of fusion system than without using the facial makeup information.

Document Doi Bibtex

Title:Integrating facial makeup detection into multimodal biometric user verification system
Department:Digital Security
Eurecom ref:5184
Copyright: © 2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+5184, doi = {}, year = {2017}, title = {{I}ntegrating facial makeup detection into multimodal biometric user verification system}, author = {{D}erman, {E}kberjan and {G}aldi, {C}hiara and {D}ugelay, {J}ean-{L}uc}, booktitle = {{IWBF} 2017, 5th {I}nternational {W}orkshop on {B}iometrics and {F}orensics, 4-5 {A}pril 2017, {C}oventry, {UK} }, address = {{C}oventry, {UNITED} {KINGDOM}}, month = {04}, url = {} }
See also: