On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition
With the rise of deep neural networks, the performance of biometric systems has increased tremendously. Biometric systems for face recognition are now used in everyday life, e.g., border control, crime prevention, or personal device access control. Although the accuracy of face recognition systems i...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | IET Biometrics |
| Online Access: | http://dx.doi.org/10.1049/2024/1808587 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825199938222424064 |
|---|---|
| author | Jascha Kolberg Yannik Schäfer Christian Rathgeb Christoph Busch |
| author_facet | Jascha Kolberg Yannik Schäfer Christian Rathgeb Christoph Busch |
| author_sort | Jascha Kolberg |
| collection | DOAJ |
| description | With the rise of deep neural networks, the performance of biometric systems has increased tremendously. Biometric systems for face recognition are now used in everyday life, e.g., border control, crime prevention, or personal device access control. Although the accuracy of face recognition systems is generally high, they are not without flaws. Many biometric systems have been found to exhibit demographic bias, resulting in different demographic groups being not recognized with the same accuracy. This is especially true for facial recognition due to demographic factors, e.g., gender and skin color. While many previous works already reported demographic bias, this work aims to reduce demographic bias for biometric face recognition applications. In this regard, 12 face recognition systems are benchmarked regarding biometric recognition performance as well as demographic differentials, i.e., fairness. Subsequently, multiple fusion techniques are applied with the goal to improve the fairness in contrast to single systems. The experimental results show that it is possible to improve the fairness regarding single demographics, e.g., skin color or gender, while improving fairness for demographic subgroups turns out to be more challenging. |
| format | Article |
| id | doaj-art-2dce463f02cd4bfb838c7fa898745555 |
| institution | Kabale University |
| issn | 2047-4946 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-2dce463f02cd4bfb838c7fa8987455552025-02-08T00:00:10ZengWileyIET Biometrics2047-49462024-01-01202410.1049/2024/1808587On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face RecognitionJascha Kolberg0Yannik Schäfer1Christian Rathgeb2Christoph Busch3da/sec–Biometrics and Security Research Groupda/sec–Biometrics and Security Research Groupda/sec–Biometrics and Security Research Groupda/sec–Biometrics and Security Research GroupWith the rise of deep neural networks, the performance of biometric systems has increased tremendously. Biometric systems for face recognition are now used in everyday life, e.g., border control, crime prevention, or personal device access control. Although the accuracy of face recognition systems is generally high, they are not without flaws. Many biometric systems have been found to exhibit demographic bias, resulting in different demographic groups being not recognized with the same accuracy. This is especially true for facial recognition due to demographic factors, e.g., gender and skin color. While many previous works already reported demographic bias, this work aims to reduce demographic bias for biometric face recognition applications. In this regard, 12 face recognition systems are benchmarked regarding biometric recognition performance as well as demographic differentials, i.e., fairness. Subsequently, multiple fusion techniques are applied with the goal to improve the fairness in contrast to single systems. The experimental results show that it is possible to improve the fairness regarding single demographics, e.g., skin color or gender, while improving fairness for demographic subgroups turns out to be more challenging.http://dx.doi.org/10.1049/2024/1808587 |
| spellingShingle | Jascha Kolberg Yannik Schäfer Christian Rathgeb Christoph Busch On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition IET Biometrics |
| title | On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition |
| title_full | On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition |
| title_fullStr | On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition |
| title_full_unstemmed | On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition |
| title_short | On the Potential of Algorithm Fusion for Demographic Bias Mitigation in Face Recognition |
| title_sort | on the potential of algorithm fusion for demographic bias mitigation in face recognition |
| url | http://dx.doi.org/10.1049/2024/1808587 |
| work_keys_str_mv | AT jaschakolberg onthepotentialofalgorithmfusionfordemographicbiasmitigationinfacerecognition AT yannikschafer onthepotentialofalgorithmfusionfordemographicbiasmitigationinfacerecognition AT christianrathgeb onthepotentialofalgorithmfusionfordemographicbiasmitigationinfacerecognition AT christophbusch onthepotentialofalgorithmfusionfordemographicbiasmitigationinfacerecognition |