The Impact of Image Resolution on Face Detection: A Comparative Analysis of MTCNN, YOLOv XI and YOLOv XII models

TL;DR

This study evaluates how different image resolutions affect the performance of three face detection models, revealing that YOLOv11 generally offers superior accuracy at higher resolutions, with implications for real-world applications.

Contribution

It systematically compares the impact of input resolution on YOLOv11, YOLOv12, and MTCNN face detectors using comprehensive metrics and the WIDER FACE dataset.

Findings

YOLOv11 outperforms others in detection accuracy at high resolutions

YOLOv12 has slightly better recall across resolutions

MTCNN offers good landmark localization but slower inference

Abstract

Face detection is a crucial component in many AI-driven applications such as surveillance, biometric authentication, and human-computer interaction. However, real-world conditions like low-resolution imagery present significant challenges that degrade detection performance. In this study, we systematically investigate the impact of input resolution on the accuracy and robustness of three prominent deep learning-based face detectors: YOLOv11, YOLOv12, and MTCNN. Using the WIDER FACE dataset, we conduct extensive evaluations across multiple image resolutions (160x160, 320x320, and 640x640) and assess each model's performance using metrics such as precision, recall, mAP50, mAP50-95, and inference time. Results indicate that YOLOv11 outperforms YOLOv12 and MTCNN in terms of detection accuracy, especially at higher resolutions, while YOLOv12 exhibits slightly better recall. MTCNN, although competitive in landmark localization, lags in real-time inference speed. Our findings provide actionable insights for selecting resolution-aware face detection models suitable for varying operational constraints.