Review on the effects of age, gender, and race demographics on automatic face recognition
Review on the effects of age, gender, and race demographics on automatic face recognition
复制标题
年龄、性别和种族人口统计对自动人脸识别的影响综述
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
A. B. Huddin
中科院分区：
文献类型：
--
作者：
Salem Hamed Abdurrahim;S. Samad;A. B. Huddin
人脸识别算法的性能受到外部因素和内部主体特征的影响。识别这些方面并了解它们对性能的影响有助于预测算法的性能，并有助于在预期位置设计合适的采集设置以提高性能。影响人脸识别系统性能的因素，如姿态、光照、表情和图像分辨率等，被认为是人脸识别问题。这些都进行了大量的研究，并已开发出许多算法来解决这些问题。然而，人口统计学的影响（即，种族、年龄和性别）对人脸识别性能的影响尚未受到相当大的关注。关于人口影响的早期发现给出了相互矛盾的结果。过去十年进行的研究解决了一些争论。尽管如此，一些研究结果尚未达成共识。现有的审查的影响，协变量是过时的，或不包括人口统计协变量的人脸识别算法的性能的影响。本文对人口统计学协变量的最新研究进行了深入而有针对性的综述。基于这些发现，总结了年龄，性别和种族协变量对人脸识别的影响，并对该领域的未来发展方向提出了建议，以充分了解这些影响及其相互作用。
The performance of face recognition algorithms is affected by external factors and internal subject characteristics. Identifying these aspects and understanding their behaviors on performance can aid in predicting the performance of algorithms and in designing suitable acquisition settings at prospective locations to enhance performance. Factors that affect the performance of face recognition systems, such as pose, illumination, expression, and image resolution, are recognized as face recognition problems. These are substantially studied, and many algorithms have been developed to tackle these problems. However, the influence of population demographics (i.e., race, age, and gender) on face recognition performance has not received considerable attention. Early findings that deal with demographic influence give conflicting results. The studies conducted in the last decade resolve some of the contentions. Nonetheless, some findings have not reached consensus. Existing reviews on the influence of covariates are either outdated or do not cover the influence of demographic covariates on the performance of face recognition algorithms. This paper gives an intensive and focused review that covers recent research on demographic covariates. The effects of age, gender, and race covariates on face recognition are summarized based on these findings, and suggestions on the future direction of the field are given to have a significant understanding of these effects individually and their interactions with one another.