Design of Real-Time Face Recognition and Emotion Recognition on Humanoid Robot Using Deep Learning
A robot is capable of mimicking human beings, including recognizing their faces and emotions. However, current studies of the humanoid robot have not been implemented in the real-time system. In addition, face recognition and emotion recognition have been treated as separate problems. Thus, for real-time application on a humanoid robot, this study proposed a combination of face recognition and emotion recognition. Face and emotion recognition systems were developed concurrently in this study using convolutional neural network architectures. The proposed architecture was compared to the well-known architecture, AlexNet, to determine which architecture would be better suited for implementation on a humanoid robot. Primary data from 30 respondents was used for face recognition. Meanwhile, emotional data were collected from the same respondents and combined with secondary data from a 2500-person dataset. Surprise, anger, neutral, smile, and sadness were among the emotions. The experiment was carried out in real-time on a humanoid robot using the two architectures. Using the AlexNet model, the accuracy of face and emotion recognition was 87 % and 70 %, respectively. Meanwhile, the proposed architecture achieved accuracy rates of 95 % for face recognition and 75 % for emotion recognition, respectively. Thus, the proposed method performs better in terms of recognizing faces and emotions, and it can be implemented on a humanoid robot.
A. Dzedzickis, A. Kaklauskas, and V. Bucinskas, “Human emotion recognition: Review of sensors and methods,” Sensors, vol. 20, no. 3, p.592., 2020.
S. Madanny, Samsuryadi,N. Yusliani, “Face Recognition Using Hyper Sausage Neuron Networks,” in Sriwijaya International Conference on Information Technology and Its Applications (SICONIAN 2019), pp. 480-484, 2020.
H. Zhi, and S. Liu, “Face recognition based on genetic algorithm,” Journal of Visual Communication and Image Representation, vol. 58, pp.495-502, 2019
T.A. Mohammed, A. Alazzawi, O.N. Uçan, and O. Bayat, “Neural network behavior analysis based on transfer functions MLP & RB in face recognition,” In Proceedings of the First International Conference on Data Science, E-learning and Information Systems, pp. 1-6, 2018.
H. Zhang, A. Jolfaei, and M. Alazab, “A face emotion recognition method using convolutional neural network and image edge computing,” IEEE Access, vol. 7, pp. 159081–159089, 2019.
K. Bahreini, W. Van der Vegt, and W. Westera, “A fuzzy logic approach to reliable real-time recognition of facial emotions,” Multimedia Tools and Applications, vol. 78, no. 14, pp.18943-18966, 2019
A. Adeyanju, E. O. Omidiora, and O. F. Oyedokun, “Performance evaluation of different support vector machine kernels for face emotion recognition,” IntelliSys 2015 - Proc. 2015 SAI Intell. Syst. Conf., pp. 804–806, 2015. doi: 10.1109/IntelliSys.2015.7361233.
G. Sharma, “CK+48 5 Emotions,” 2019. [Online]. Available: https://www.kaggle.com/datasets/gauravsharma99/ck48-5-emotions.
J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, and T. Chen, “Recent advances in convolutional neural networks,” Pattern Recognition, vol. 77, pp.354-377, 2018.
S. Dwijayanti, R.R. Abdillah, H. Hikmarika, Z. Husin, and B.Y. Suprapto, “Facial Expression Recognition and Face Recognition Using a Convolutional Neural Network,” In 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), pp. 621-626, 2020.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks, “Advances in neural information processing systems, vol. 25, 2012.
Copyright (c) 2022 Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article is the property of the author.
- The author acknowledges that the Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) has the right to publish for the first time with a Creative Commons Attribution 4.0 International License.
- The author can enter the writing separately, regulate the non-exculsive distribution of manuscripts that have been published in this journal into other versions (for example: sent to the author's institution respository, publication into books, etc.), by acknowledging that the manuscript was first published in the Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering);