Abstract
The research aims to evaluate the impact of race in facial recognition across two types of algorithms. We give a general insight into facial recognition and discuss four problems related to facial recognition. We review our system design, development, and architectures and give an in-depth evaluation plan for each type of algorithm, dataset, and a look into the software and its architecture. We thoroughly explain the results and findings of our experimentation and provide analysis for the machine learning algorithms and deep learning algorithms. Concluding the investigation, we compare the results of two kinds of algorithms and compare their accuracy, metrics, miss rates, and performances to observe which algorithms mitigate racial bias the most. We evaluate racial bias across five machine learning algorithms and three deep learning algorithms using racially imbalanced and balanced datasets. We evaluate and compare the accuracy and miss rates between all tested algorithms and report that SVC is the superior machine learning algorithm and VGG16 is the best deep learning algorithm based on our experimental study. Our findings conclude the algorithm that mitigates the bias the most is VGG16, and all our deep learning algorithms outperformed their machine learning counterparts.
Highlights
Many biometrics exist to provide authentication for users while in a public setting [1], such as personal identification numbers, passwords, cards, keys, and tokens [2]
We present our findings in hopes of making a meaningful contribution to the decades-old computer vision problem and facial recognition fields
Much like machine learning was a form of data mining, deep learning algorithms are a subset of machine learning that functions but with differing capabilities [27]
Summary
Many biometrics exist to provide authentication for users while in a public setting [1], such as personal identification numbers, passwords, cards, keys, and tokens [2]. Plenty of facial recognition algorithm variants exist [18,19], and together these algorithms can improve human capabilities in security, medicine, social sciences [17], marketing, and human–machine interface [20] These algorithms possess the ability to detect faces, sequence, gait, body, and gender determination [19], but still, trained algorithms can produce skewed results [16,17]. The results include an imbalance for some races and demographical bias against specific ethnicities Considering these inequalities, we investigate and evaluate racial discrimination in facial recognition across the various machine and deep learning models. Collecting the results from the deep learning models, we perform identical evaluation and bias measurements.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have