Is Facial Recognition Biased at Near-Infrared Spectrum as Well?
Is Facial Recognition Biased at Near-Infrared Spectrum as Well?
复制标题
DOI：
10.1109/hst56032.2022.10025433
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Anoop Krishnan;B. Neas;A. Rattani
中科院分区：
文献类型：
--
作者：
Anoop Krishnan;B. Neas;A. Rattani
已发表的学术研究和媒体文章表明，人脸识别在人口统计学上存在偏见。具体而言，女性、深色皮肤的人和老年人的表现不平等。然而，这些已发表的研究已经检查了可见光谱（维斯）中面部识别的偏差。面部化妆、面部毛发、肤色和照明变化等因素已被归因于该技术在维斯下的偏差。近红外（NIR）光谱在对照明变化、面部化妆和肤色等因素的鲁棒性方面优于维斯。因此，研究近红外光谱人脸识别的偏差是一个非常重要的课题。本研究首先探讨人脸辨识系统在近红外光谱下的偏差。为此，两个流行的近红外人脸图像数据集，即CASIA-Face-Africa和NotreDame-NIVL，分别由非洲人和白人受试者组成，被用来研究面部识别技术在性别和种族上的偏见。有趣的是，实验结果表明，在近红外光谱下，不同性别和种族的人脸识别性能相同。
Published academic research and media articles suggest face recognition is biased across demographics. Specifically, unequal performance is obtained for women, dark-skinned people, and older adults. However, these published studies have examined the bias of facial recognition in the visible spectrum (VIS). Factors such as facial makeup, facial hair, skin color, and illumination variation have been attributed to the bias of this technology at VIS. The near-infrared (NIR) spectrum offers an advantage over VIS in terms of robustness to factors such as illumination changes, facial make-up, and skin color. Therefore, it is worth-while to investigate the bias of the facial recognition at near-infrared spectrum (NIR). This first study investigates the bias of face recognition system at NIR spectrum. To this aim, two popular NIR facial image datasets namely, CASIA-Face-Africa and NotreDame-NIVL consisting of African and Caucasian subjects, respectively, are used to investigate the bias of facial recognition technology across gender and race. Interestingly, experimental results suggest equitable performance of the face recognition across gender and race at NIR spectrum.