Addressing Demographic Bias in Age Estimation Models through Optimized Dataset Composition

Abstract

Bias in facial recognition systems often results in unequal performance across demographic groups. This study addresses this by investigating how dataset composition affects the performance and bias of age estimation models across ethnicities. We fine-tuned pre-trained Convolutional Neural Networks (CNNs) like VGG19 on the diverse UTKFace dataset (23,705 samples: 10,078 White, 4526 Black, 3434 Asian) and APPA-REAL (7691 samples: 6686 White, 231 Black, 674 Asian). Our approach involved adjusting dataset compositions by oversampling minority groups or reducing samples from overrepresented groups to mitigate bias. We conducted experiments to identify the optimal dataset composition that minimizes performance disparities among ethnic groups. The primary performance metric was Mean Absolute Error (MAE), measuring the average magnitude of prediction errors. We also analyzed the standard deviation of MAE across ethnic groups to assess performance consistency and equity. Our findings reveal that simple oversampling of minority groups does not ensure equitable performance. Instead, systematic adjustments, including reducing samples from overrepresented groups, led to more balanced performance and lower MAE standard deviations across ethnicities. These insights highlight the importance of tailored dataset adjustments and suggest exploring advanced data processing methods and algorithmic tweaks to enhance fairness and accuracy in facial recognition technologies.