Face Recognition Algorithm Bias: Performance Differences on Images of Children and Adults

Srinivas, Nisha; Ricanek, Karl; Michalski, Dana; Bolme, David S.; King, Michael C.

doi:10.1109/cvprw.2019.00280

Cited by 53 publications

(46 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, several works have been published that demonstrated the influence of demographics on commercial and open-sources face recognition algorithms. Studies [56], [46], [16], [66] analysing the impact of age demonstrated a lower biometric performance on faces of children. Studies [76], [3], [2], [61] analysing the effect of gender on face recognition showed that the recognition performance of females is weaker than the performance on male faces.…”

Section: A Estimating Bias In Face Recognitionmentioning

confidence: 99%

“…Identities Images Attributes (number classes) Ricanek et al [56] 0.7k 8.0k Age (2) Deb et al [16] 0.9k 3.7k Age (cont.) Srinivas et al [66] 1.7k 9.2k Age (2) Michalski et al [46] -4.7M Age (cont.) Albiero et al [2] 26.9k 151.6k Gender (2) Albiero et al [3] 15.9k 101.3k Gender (2) Vera-Rodriguez et al [76] 0.5k 169.4k Gender (2) Cavazos et al [9] 0.4k 1.1k Ethnicity (2) Krishnapriya et al [41] 22.7k 3.3M Gender (2), Ethnicity (2) Serna et al [ 47 attributes represent a step forward in the literature in comparison with previous analyses focused on no more than seven attributes [44].…”

Section: Workmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Terhörst

Kolf

Huber

et al. 2022

IEEE Trans. Technol. Soc.

View full text Add to dashboard Cite

Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. However, to enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR beyond demographics. Therefore, in this work, we analyse FR bias over a wide range of attributes. We investigate the influence of 47 attributes on the verification performance of two popular FR models. The experiments were performed on the publicly available MAAD-Face attribute database with over 120M high-quality attribute annotations. To prevent misleading statements about biased performances, we introduced control group based validity values to decide if unbalanced test data causes the performance differences. The results demonstrate that also many non-demographic attributes strongly affect the recognition performance, such as accessories, hair-styles and colors, face shapes, or facial anomalies. The observations of this work show the strong need for further advances in making FR system more robust, explainable, and fair. Moreover, our findings might help to a better understanding of how FR networks work, to enhance the robustness of these networks, and to develop more generalized bias-mitigating face recognition solutions.

show abstract

Section: A Estimating Bias In Face Recognitionmentioning

confidence: 99%

Section: Workmentioning

confidence: 99%

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Terhörst

Kolf

Huber

et al. 2022

IEEE Trans. Technol. Soc.

View full text Add to dashboard Cite

show abstract

“…However, in order to be acceptable in a practical context, that performance level must be retained when implemented in a real-world context, using non-pristine images, and in a cost/form factor that is realistic for a store to deploy. Further, knowing that many machine-learning solutions are susceptible to degradation resulting from training dataset mismatch with respect to ethnicity [11], gender [12], image quality [13], lighting conditions [14], and combinations of these parameters with other characteristics [15][16][17], we chose to intentionally bombard the neural net model with different presentation attacks to quantify how quickly performance degrades.…”

Section: Motivationmentioning

confidence: 99%

Real-Time Mask Recognition

Billings

Michaels

2021

IoT

View full text Add to dashboard Cite

While a variety of image processing studies have been performed to quantify the potential performance of neural network-based models using high-quality still images, relatively few studies seek to apply those models to a real-time operational context. This paper seeks to extend prior work in neural-network-based mask detection algorithms to a real-time, low-power deployable context that is conducive to immediate installation and use. Particularly relevant in the COVID-19 era with varying rules on mask mandates, this work applies two neural network models to inference of mask detection in both live (mobile) and recorded scenarios. Furthermore, an experimental dataset was collected where individuals were encouraged to use presentation attacks against the algorithm to quantify how perturbations negatively impact model performance. The results from evaluation on the experimental dataset are further investigated to identify the degradation caused by poor lighting and image quality, as well as to test for biases within certain demographics such as gender and ethnicity. In aggregate, this work validates the immediate feasibility of a low-power and low-cost real-time mask recognition system.

show abstract

“…Specifically, the authors propose a score normalization scheme to handle the problem of inaccurate performance ratings when comparing demographicspecific performances to the average-a problem we highlighted in [11], and which we now extend. Some aim to characterize the amount of bias in a system, whether for gender [28]- [30], ethnicity, age [31], or more than one [32]- [36]. A recent European Conference on Computer Vision (ECCV) challenge provided an incentive for researchers to tackle bias concerning ethnicity, gender, age, pose, and with and without sunglasses [37].…”

Section: Bias In Frmentioning

confidence: 99%

Balancing Biases and Preserving Privacy on Balanced Faces in the Wild

Robinson¹,

Qin²,

Henon³

et al. 2021

Preprint

View full text Add to dashboard Cite

There are demographic biases in current models used for facial recognition (FR). Our Balanced Faces In the Wild (BFW) dataset serves as a proxy to measure bias across ethnicity and gender subgroups, allowing one to characterize FR performances per subgroup. We show performances are non-optimal when a single score threshold is used to determine whether sample pairs are genuine or imposter. Across subgroups, performance ratings vary from the reported across the entire dataset. Thus, claims of specific error rates only hold true for populations matching that of the validation data. We mitigate the imbalanced performances using a novel domain adaptation learning scheme on the facial features extracted using state-of-the-art. Not only does this technique balance performance, but it also boosts the overall performance. A benefit of the proposed is to preserve identity information in facial features while removing demographic knowledge in the lower dimensional features. The removal of demographic knowledge prevents future potential biases from being injected into decision-making. This removal satisfies privacy concerns. We explore why this works qualitatively; we also show quantitatively that subgroup classifiers can no longer learn from the features mapped by the proposed.

show abstract

Face Recognition Algorithm Bias: Performance Differences on Images of Children and Adults

Cited by 53 publications

References 10 publications

A Comprehensive Study on Face Recognition Biases Beyond Demographics

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Real-Time Mask Recognition

Balancing Biases and Preserving Privacy on Balanced Faces in the Wild

Contact Info

Product

Resources

About