Real-Time Face Age Detection System Based on Deep Neural Networks with MediaPipe Optimization for Enhanced Accuracy
Abstract
The transformation of machine learning and computer vision technology enables computers to automatically learn complex visual patterns, forming the foundation for biometric applications such as identity authentication, face detection, and demographic analytics. Face age estimation predicts age based on facial characteristics in digital images with high accuracy. Handcrafted feature-based approaches such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) are less stable against variations in lighting, camera orientation, and facial expressions. Deep learning, particularly Deep Neural Networks (DNN), improves accuracy through automatic hierarchical feature extraction. However, raw image-based methods have high computational loads and require large GPUs, which are less than ideal for real-time use on limited devices. This research proposes a DNN-based age estimation system optimized through MediaPipe Face Mesh geometric features. The system consists of five layers: input, feature extraction (468 facial landmarks), optimization with Principal Component Analysis (PCA) for 64 features, DNN regression (three hidden layers), and output. A custom dataset of 1,235 facial images (ages 3–40 years) was divided into 80% training and 20% testing. The model was trained with the Adam optimizer (learning rate 0.001, epochs 500, loss MAE). Evaluation results: MAE 0.56 years, RMSE 1.94 years, R² 0.9726. Tolerance accuracy: 91% (±1 year), 96.7% (±2 years), 97.5% (±3 years), 99.2% (±5 years). An efficient system for real-time use on low-computing devices, supporting biometric applications such as security, content filtering, personalization, and health. This research contributes to accurate, lightweight, and adaptive age estimation systems.
Downloads
References
O. Abhulimen, “Facial Age Estimation Using Deep Learning: A Review,” vol. 8, no. 5, pp. 13927–13946, 2021.
X. Liu, M. Qiu, Z. Zhang, Y. Shi, Z. Li, and X. Chen, “Enhancing facial age estimation with local and global multi-attention mechanisms,” Pattern Recognit. Lett., vol. 189, no. January, pp. 71–77, 2025, doi: https://doi.org/10.1016/j.patrec.2025.01.005.
P. Jayabharathi and K. Rohini, “Accurate Age and Gender Prediction Using DNN Model from Real World Camera Feeds,” vol. 10, 2025.
R. Singh and S. Singh, “Internet of Things and Cyber-Physical Systems Edge AI: A survey,” Internet Things Cyber-Physical Syst., vol. 3, no. February, pp. 71–92, 2023, doi: https://doi.org/10.1016/j.iotcps.2023.02.004.
M. Wang and W. Chen, “Age prediction based on a small number of facial landmarks and texture features,” vol. 29, pp. 497–507, 2021, doi: https://doi.org/10.3233/THC-218047.
J. Wang, S. Yuan, T. Lu, H. Zhao, and Y. Zhao, “Video-Based Real-Time Monitoring of Engagement in E-learning Using MediaPipe Through Multi-Feature Analysis,” Expert Syst. Appl., vol. 242, 2025, doi: https://doi.org/10.1016/j.eswa.2025.125185.
T. Zhao et al., “A Survey of Deep Learning on Mobile Devices : Applications , Optimizations , Challenges , and Research Opportunities,” vol. 110, no. 3, 2022.
S. A. Jakhete and N. Kulkarni, “A Comprehensive Survey and Evaluation of MediaPipe Face Mesh for Human Emotion Recognition,” in IEEE Conference on Intelligent Systems, 2024. doi: https://doi.org/10.1109/ICIS.2024.10775188.
K. Elkarazle and V. Raman, “Facial Age Estimation Using Machine Learning Techniques: An Overview,” 2022.
I. T. Aruleba and Y. Sun, “Deep Learning and Genetic Algorithms Approach for Age Estimation Based on Facial Images,” Int. J. Comput. Theory Eng., vol. 16, no. 4, pp. 127–133, 2024.
H. Peng, W. Gong, C. F. Beckmann, A. Vedaldi, and S. M. Smith, “Accurate Brain Age Prediction with Lightweight Deep Neural Networks,” Med. Image Anal., vol. 68, p. 101871, 2021.
S. Hangaragi, T. Singh, and N. Neelima, “Face Detection and Recognition Using Face Mesh and Deep Neural Network,” Procedia Comput. Sci., vol. 218, pp. 741–749, 2023, doi: https://doi.org/10.1016/j.procs.2023.01.001. Sci., vol. 218, pp. 741–749, 2023, doi: 10.1016/j.procs.2023.01.054.
O. Guehairia, A. Ouamane, F. Dornaika, and A. Taleb-Ahmed, “Feature Fusion via Deep Random Forest for Facial Age Estimation,” Neural Networks, vol. 130, pp. 238–252, 2020.
M. Tanveer et al., “Deep Learning for Brain Age Estimation: A Systematic Review,” Inf. Fusion, vol. 96, pp. 130–143, 2023.
K. Mitrović and D. Milošević, “Pose Estimation and Joint Angle Detection Using MediaPipe Machine Learning Solution,” in Serbian International Conference on Applied Artificial Intelligence, 2022. doi: https://doi.org/10.1007/978-3-031-29717-5_8.
O. Agbo-Ajala and S. Viriri, “A Lightweight CNN for Real and Apparent Age Estimation in Unconstrained Face Images,” IEEE Access, vol. 8, pp. 162800–162808, 2020.
R. U. Karim et al., “Optimizing Stroke Recognition with MediaPipe and Machine Learning: An Explainable AI Approach for Facial Landmark Analysis,” IEEE Access, vol. 13, pp. 1–9, 2025, doi: https://doi.org/10.1109/ACCESS.2025.10924203.
A. Kjærran, C. B. Vennerød, and E. S. Bugge, “Facial Age Estimation Using Convolutional Neural Networks,” arXiv Prepr. arXiv2105.06746, 2021.
G. Sanil, K. Prakash, S. Prabhu, and V. C. Nayak, “2D–3D Facial Image Analysis Using Machine Learning Algorithms with Hyperparameter Optimization for Forensics Applications,” IEEE Access, vol. 11, pp. 7123–7137, 2023.
N. Azad, H. Moussddik, and K. El Fazazy, “Deep Learning-Based Multimodal Biometric System: A Fusion Approach Integrating Iris, Face, and Finger Vein Traits,” Arab. J. Sci. Eng., 2025, doi: https://doi.org/10.1007/s13369-025-10785-8.
V. Arya and S. Maji, “Enhancing Human Pose Estimation: A Data-Driven Approach with MediaPipe BlazePose and Feature Engineering Analysis,” in IEEE Conference on Developments in Computer Science & Digital Technology, 2024. doi: https://doi.org/10.1109/DCSDT.2024.10696215.
S. McNeil, L. H. Jacobson, and D. Claes, “Graph Neural Networks for 3D Facial Morphology: Assessing the Effectiveness of Anthropometric and Automated Landmark Detection,” Front. Artif. Intell., vol. 6, p. 1126017, 2023, doi: https://doi.org/10.3389/frai.2023.1126017.
I. A. Dahlan, D. Ariateja, M. A. Arghanie, M. A. Versantariqh, M. David, and U. D. Fatmawati, “Automatic Weapon Detection System Using Deep Learning Based on Smart CCTV,” J. Syst. , vol. 4, no. 2, pp. 126–141, 2021, doi: https://doi.org/10.37396/jsc.v4i2.172.
