The Effect of Own-Race Bias (ORB) on Face Recognition

Authors

  • Junhao Wang

DOI:

https://doi.org/10.54097/kxk18g29

Keywords:

Own race bias, racial feature, face recognition.

Abstract

The term "own-race bias" (ORB) describes the situation in which people are more adept at identifying the faces of members of their own race than those of other races. The impact of racial disparities on face recognition accuracy and speed is investigated in this study. Empirical studies have demonstrated the involvement of variables including affect and mental abilities in ORB. While split attention tends to enhance ORB, positive emotions can decrease it. Positive emotional states may also boost cognitive flexibility, which would improve the ability to recognise faces of different races. Research looking at racial disparities in facial features also show quantifiable differences across racial groups. While some studies employ deep learning algorithms to categorise race using face traits, others use anthropometric measurements to identify these differences. Notwithstanding these discoveries, additional research employing more varied samples and longer study durations is necessary due to limitations including biassed data and a disregard for the environment.

Downloads

Download data is not yet available.

References

[1] Gates, A. (2008). Face recognition: Establishing the effect of positive emotion on eliminating the cross-race deficit. University of London, University College London (United Kingdom).

[2] Johnson, K. J., & Fredrickson, B. L. (2005). "We all look the same to me": Positive emotions eliminate the own-race bias in face recognition. Psychological Science, 16 (11), 875-881. https://doi.org/10.1111/j.1467-9280.2005.01631.x.

[3] Johnson, K. J. (2005). Erasing race: Positive emotions eliminate recognition differences between own-race and other-race faces. University of Michigan.

[4] Zhou, G., Pu, X., Young, S. G., & Tse, C. S. (2014). Effects of divided attention and social categorization on the own-race bias in face recognition. Visual Cognition, 22 (9-10), 1296-1310. https://doi.org/10.1080/13506285.2014.935750.

[5] Goldstein, A. G. (1979). Race-related variation of facial features: Anthropometric data I. Bulletin of the Psychonomic Society, 13 (3), 187-190. https://doi.org/10.3758/BF03335061.

[6] Kolla, M., & Savadamuthu, A. (2023). The impact of racial distribution in training data on face recognition bias: A closer look. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 313-322). https://doi.org/10.1109/WACV55620.2023.00034.

[7] Khan, K., Ali, J., Uddin, I., Khan, S., & Roh, B. H. (2021). A facial feature discovery framework for race classification using deep learning. arXiv preprint arXiv:2104.02471. https://arxiv.org/abs/2104.02471.

[8] Chiroro, P. M., Tredoux, C. G., Radaelli, S., & Meissner, C. A. (2008). Recognizing faces across continents: The effect of within-race variations on the own-race bias in face recognition. Psychonomic Bulletin & Review, 15 (6), 1089-1092. https://doi.org/10.3758/PBR.15.6.1089.

Downloads

Published

26-12-2024