Impact of Image Resolution on Age Estimation with DeepFace and InsightFace

TL;DR

This study investigates how varying image resolutions affect age estimation accuracy using DeepFace and InsightFace, finding optimal performance at 224x224 pixels and highlighting the impact of resolution on model accuracy and speed.

Contribution

It provides a comprehensive analysis of resolution effects on age estimation accuracy for DeepFace and InsightFace, identifying optimal resolution and performance trade-offs.

Findings

Optimal performance at 224x224 pixels with MAE of 10.83 and 7.46 years

Lower resolutions significantly increase MAE

InsightFace is faster than DeepFace across all resolutions

Abstract

Automatic age estimation is widely used for age verification, where input images often vary considerably in resolution. This study evaluates the effect of image resolution on age estimation accuracy using DeepFace and InsightFace. A total of 1000 images from the IMDB-Clean dataset were processed in seven resolutions, resulting in 7000 test samples. Performance was evaluated using Mean Absolute Error (MAE), Standard Deviation (SD), and Median Absolute Error (MedAE). Based on this study, we conclude that input image resolution has a clear and consistent impact on the accuracy of age estimation in both DeepFace and InsightFace. Both frameworks achieve optimal performance at 224x224 pixels, with an MAE of 10.83 years (DeepFace) and 7.46 years (InsightFace). At low resolutions, MAE increases substantially, while very high resolutions also degrade accuracy. InsightFace is consistently faster than DeepFace across all resolutions.