December 4, 2025Applied System InnovationOpen Access

Enhancing the Effectiveness of Juvenile Protection: Deep Learning-Based Facial Age Estimation via JPSD Dataset Construction and YOLO-ResNet50

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Facial age estimation shows 89.17% Recall for ages 0-8, indicating deep learning aids juvenile protection efforts.

Deep learning enhances image classification for juvenile age estimation in adult venues, significantly improving supervision.
The framework achieved high Recall of 89.17% for age group 0-8 using YOLO for object detection and ResNet50 for classification.
Utilizing multiple datasets, including UTKface and MegaAge, we constructed the JPSD dataset for robust training and evaluation.
The findings underline the critical need for human supervision despite high accuracy, particularly in middle age groups.

Wu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark