Leveraging the Deep Learning Tools and Technique for Enhanced Biometrics and Facial Emotion Based Predictions for Customised Applications
Ahmed Abbas Naqvi
New Delhi, India
Download PDFAbstract
In today's society, the use of machines for various tasks is rising. Machines can perform a wide range of tasks when given perception. There are also very difficult ones, like elderly care. Understanding the interlocutor's intentions and surrounding environment is necessary for machine perception. In this regard, facial emotion recognition can be helpful. Images depicting facial emotions like happiness, sadness, anger, surprise, disgust, and fear were used in the development of this work with deep learning techniques. A pure convolutional neural network approach outperformed other authors' statistical methods, such as feature engineering, in this study. There is a learning function that can be used with convolutional networks. This seems promising for this job, where it takes time to define the functionality. Two distinct corpora were also used to evaluate the network. One was used to help define the network's architecture and fine-tune parameters during network training. Mimic emotions made up this corpus. The network with the highest classification accuracy results was tested on the second dataset. Even though the network was only trained on one corpus, when it was tested on another dataset with non-real facial emotions, it showed promising results. The obtained results needed to meet current standards. Evidence suggests that facial expression classification may benefit from deep learning. As a result, deep learning has the potential to enhance interaction between humans and machines. Because machines can develop cognition through the ability to learn new functions, the machine can respond more smoothly through perception, greatly enhancing the user experience.
Keywords: Deep learning Algorithm; biometrics; facial emotion prediction; FACS (Facial Action Coding System)
- Y.-L. Tian, T. Kanade, and J. F. Cohn, (2001), Recognizing action units for facial expression analysis, Proc. IEEE Conf. Comput. Vis. Pattern Recognit. CVPR 2000 Cat NoPR00662, vol. 1, no. 2, pp. 1–19.
- F. De la Torre and J. F. Cohn, (2011), Facial expression analysis, Vis. Anal. Hum., pp. 377–410.
- A. Gudi, H. E. Tasli, T. M. Den Uyl, and A. Maroulis, (2015), Deep Learning based FACS Action Unit Occurrence and Intensity Estimation, 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
- Z. Ming et al., (2015), Facial Action Units Intensity Estimation by the Fusion of Features with Multi-kernel Support Vector Machine To cite this version : Facial Action Units Intensity Estimation by the Fusion of Features with Multi-kernel Support Vector Machine, 11TH IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
- R. S. Smith and T. Windeatt, (2015), Facial action unit recognition using multi-class classification, Neurocomputing, vol. 150, pp. 440–448.
- S. Taheri, Qiang Qiu, and R. Chellappa, (2014), Structure-preserving sparse decomposition for facial expression analysis., IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc., vol. 23, no. 8, pp. 3590–603.
- Y. Wu and Q. Ji, (2015), Discriminative Deep Face Shape Model for Facial Point Detection, Int. J. Computer. Vision., vol. 113, no. 1, pp. 37–53.
- M. F. Valstar and M. Pantic, (2012), Fully automatic recognition of the temporal phases of facial actions, IEEE Trans. Syst. Man Cybern. Part B Cybern., vol. 42, no. 1, pp. 28–43.
- L. Wang, R. Li, and K. Wang, (2014), A Novel Automatic Facial Expression Recognition Method Based on AAM, J. Comput., vol. 9, no. 3, pp. 608–617.