Smart Facial Recognition with Age Estimation, Gender Classification and Emotion Detection
DOI:
https://doi.org/10.48001/978-81-966500-7-0-2Keywords:
K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Deep learning, Convolutional Neural Networks (CNN) -16Abstract
The field of Affective Computing has witnessed significant interest in real-time facial expression recognition (FER) due to advancements in machine learning (ML) and deep learning (DL) techniques. Integrating an ER system with a digital representation of an individual allows effective monitoring, understanding, and enhancement of their physical well-being. This approach provides continuous feedback to improve overall wellness through personalized healthcare. However, developing real-time ER systems poses challenges such as limited datasets, feature identification, emotion classification, and high implementation costs. To address these hurdles, we propose a straightforward and adaptable ER system that processes real-time image data captured via a webcam. Our study introduces a system designed to recognize human emotional states from facial expressions, alongside methods for predicting age and gender from facial features. We also explore how gender and age impact facial expressions. The proposed system detects seven emotions: Anger, Disgust, Happy, Fear, Sad, Surprise, and Neutral states, based on facial data. It comprises three main components: Gender Detection, Age Detection, and Emotion Recognition. We employ two algorithms, K-Nearest Neighbours (KNN) and Support Vector Machine (SVM), along with deep learning models like Convolutional Neural Networks (CNN) and VGG-16 through Transfer Learning. Our ER system demonstrates promising results with reduced training time while maintaining accuracy. By bridging the gap between technology and human emotions, we pave the way for improved personalized healthcare and well-being.
Downloads
References
Anusha, K., Vasumathi, D., & Mittal, P. (2023). A Framework to Build and Clean Multilanguage Text Corpus for Emotion Detection using Machine Learning. Journal of Theoretical and Applied Information Technology, 101(3), 1344–1350.
Dalvi, C., Rathod, M., Patil, S., Gite, S., & Kotecha, K. (2021). A Survey of AI-Based Facial Emotion Recognition: Features, ML DL Techniques, Age-Wise Datasets and Future Directions. IEEE Access, 9, 165806–165840. https://doi.org/10.1109/ACCESS.2021.3131733
ELKarazle, K., Raman, V., & Then, P. (2022). Facial Age Estimation Using Machine Learning Techniques: An Overview. Big Data and Cognitive Computing, 6(4). https://doi.org/10.3390/bdcc6040128
Kumar, N., Berg, A. C., Belhumeur, P. N., & Nayar, S. K. (2009). Attribute and simile classifiers for face verification. Proceedings of the IEEE International Conference on Computer Vision, 365–372. https://doi.org/10.1109/ICCV.2009.5459250
Kumari, N., & Bhatia, R. (2022). Efficient facial emotion recognition model using deep convolutional neural network and modified joint trilateral filter. Soft Computing, 26(16), 7817–7830. https://doi.org/10.1007/s00500-022-06804-7
Levi, G., & Hassncer, T. (2015). Age and gender classification using convolutional neural networks. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2015-Octob, 34–42. https://doi.org/10.1109/CVPRW.2015.7301352
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision, 2015 Inter, 3730–3738. https://doi.org/10.1109/ICCV.2015.425
Mittal, P., & Gautam, S. (2023). Logistic Regression and Predictive Analysis in Public Services of AI Strategies. TEM Journal, 12(2), 751–756. https://doi.org/10.18421/TEM122-19
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). DeepFace: Closing the gap to human-level performance in face verification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1701–1708. https://doi.org/10.1109/CVPR.2014.220
Teja Chavali, S., Tej Kandavalli, C., Sugash, T. M., & Subramani, R. (2022). Smart Facial Emotion Recognition with Gender and Age Factor Estimation. Procedia Computer Science, 218, 113–123. https://doi.org/10.1016/j.procs.2022.12.407
YILDIZ, K., GÜNEŞ, E., & BAS, A. (2021). CNN-based Gender Prediction in Uncontrolled Environments. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 9(2), 890–898. https://doi.org/10.29130/dubited.763427
Zahara, L., Musa, P., Prasetyo Wibowo, E., Karim, I., & Bahri Musa, S. (2020). The Facial Emotion Recognition (FER-2013) Dataset for Prediction System of MicroExpressions Face Using the Convolutional Neural Network (CNN) Algorithm based Raspberry Pi. 2020 5th International Conference on Informatics and Computing, ICIC 2020. https://doi.org/10.1109/ICIC50835.2020.9288560
Zhang, H., Zhang, Y., & Geng, X. (2021). Practical age estimation using deep label distribution learning. Frontiers of Computer Science, 15(3). https://doi.org/10.1007/s11704-020-8272-4
Zhang, Y., Liu, L., Li, C., & Loy, C. C. (2017). Quantifying facial age by posterior of age comparisons. British Machine Vision Conference 2017, BMVC 2017. https://doi.org/10.5244/c.31.108
Zhang, Z., Song, Y., & Qi, H. (2017). Age progression/regression by conditional adversarial autoencoder. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-Janua, 4352–4360. https://doi.org/10.1109/CVPR.2017.463
