Analysis of Facial Sentiments : A Deep-Learning Way
Keywords:
RESNET, VGG, Deep Learning, Facial sentiment, FER 2013.Abstract
Human looks are an important way to convey emotions. In the field of PC vision, the programmed examination of these implicit opinions has been a fascinating and challenging endeavor with applications in a variety of fields, including brain research, product promotion, process robotization, and so on. This task has been hard because there are so many different ways people express their emotions through expression. Already, different strategies for AI, like Irregular timberland and SVM, were utilized to utilize changed pictures over completely to anticipate the opinion. In many areas of research, including PC vision, deep learning has been crucial to making progress. We use a model based on a convolutional neural network (CNN) to detect facial sentiment. For testing and training, the FER-2013 public dataset is utilized.
References
- A. N. Wiens, R. G. Harper and J. D. Matarazzo, Nonverbal correspondence: the most recent development. 1978, J. Wiley & Sons
- M. J. Jones and P. Viola, "Hearty ongoing face location," Global diary of PC vision, vol. 57, no. 2, pp. 137–154, 2004.
- Jane, Philippa E. Pattison, Henry J. Jackson, and Edwards. In schizophrenia, emotion recognition through facial expression and affective prosody: a strategic survey." Clinical brain research audit 22.6: 789-832, 2002.
- Chu, William Wei-Jen Tsai, Hui-Chuan, YuhMin Chen and Min-Ju Liao. " In adaptive e-learning, "Facial expression recognition with transition detection for students with high-functioning autism." Software Computing: 1-27, 2017.
- Clavel, Iona Vasilescu, Laurence Devillers, Gal Richard, and Thibaut Ehrette are the members of this group. emotion recognition in the style of fear for future audio-based surveillance systems." 50, 2008, Speech Communication
- Cowie, Nicolas Tsapatsoulis, Ellen Douglas-Cowie, Roddy, Winfried Fellenz,George Votsis, Stefanos Kollias, and John G. Taylor. " The use of emotion recognition in computer-human interaction. No. 18 of IEEE Signal Processing Magazine 1: 32-80, 2001.
- Pooya, Thomas Huang, Khorrami, and Thomas Paine. " When it comes to expression recognition, do deep neural networks learn facial action units? in the IEEE Computer Conference. Vision. 2015.
- Deepali, Alex Colburn, Aneja, Gary Faigin, Barbara Mones, and Linda Shapiro. Utilizing deep learning to model stylized character expressions." Pages of the Asian Conference on Computer Vision 136-153. Springer, 2016.
- Paul, Ekman, and W.V. Friesen. " Across cultures, the face and emotion remain constant." 1971, Personality and Social Psychology Journal
- LeCun, Y. Speculation and organization plan methodologies. Perspectives on connectionism, 143-155, 1989.
- The FER-2013 database was created by I. J. Carrier, P. L. Mirza, A. Courville, M. Goodfellow, and Y. Bengio. 2013 from the University of Montreal
- H. Mliki, H. BenAbdallah, M. Hammami, and N. Fourati, "Information miningbased looks acknowledgment framework." SCAI, 2013, pages 185– 194.
- "Facial expression recognition via a boosted deepbelief network," published in the IEEE Conference on Computing, by P. Liu, Y. Tong, Z. Meng, and S. Han. Vision and Example Rec., pp. 1805-1812. 2014.
- O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, and a number of other individuals Large-scale visual recognition challenge from Imagenet. 2014, arXiv preprint arXiv:1409.0575
- Computer Vision Image Understand, “Local binary patterns for multi-view facial expression recognition,” by S. Moore and R. Bowden. vol. 115, no. 4, pp. 541–558, 2011.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT

This work is licensed under a Creative Commons Attribution 4.0 International License.