Facial expression recognition has become an increasingly important area of research in recent years. Neural network- based methods have made amazing progress in performing recognition-based tasks, winning competitions set up by various data science communities, and achieving high performance on many datasets. Miscellaneous regularization methods have been utilized by various researchers to help combat over-fitting, to reduce training time, and to generalize their models. In this paper, by applying the Haar Cascade classifier to crop faces and focus on the region of interest, we hypothesize that we would attain a fast convergence without using the whole image to analyze facial expressions. We also apply label smoothing and analyze its effect on the databases of CK+, KDEF, and RAF. The ResNet model has been employed as an example of a neural network model. Label smoothing has demonstrated an improvement of the recognition accuracy up to 0.5% considering CK+ and the KDEF databases. While the application of Haar Cascade has shown to decrease the achieved accuracy on KDEF and RAF databases with a small margin, fast convergence of the model has been observed.
Skip Nav Destination
Article navigation
2 March 2021
FOURTH INTERNATIONAL CONFERENCE OF MATHEMATICAL SCIENCES (ICMS 2020)
17–21 June 2020
Istanbul, Turkey
Research Article|
March 02 2021
Facial expression recognition using deep learning
Harisu Abdullahi Shehu;
Harisu Abdullahi Shehu
a)
1
Victoria University of Wellington
, New Zealand
a)Corresponding author: [email protected]
Search for other works by this author on:
Md. Haidar Sharif;
Md. Haidar Sharif
b)
2
University of Hail
, Kingdom of Saudi Arabia
Search for other works by this author on:
Sahin Uyaver
Sahin Uyaver
c)
3
Turkish-German University, Faculty of Science, Department of Energy Science and Technologies
, Istanbul, Turkey
Search for other works by this author on:
AIP Conf. Proc. 2334, 070003 (2021)
Citation
Harisu Abdullahi Shehu, Md. Haidar Sharif, Sahin Uyaver; Facial expression recognition using deep learning. AIP Conf. Proc. 2 March 2021; 2334 (1): 070003. https://doi.org/10.1063/5.0042221
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Inkjet- and flextrail-printing of silicon polymer-based inks for local passivating contacts
Zohreh Kiaee, Andreas Lösel, et al.
Effect of coupling agent type on the self-cleaning and anti-reflective behaviour of advance nanocoating for PV panels application
Taha Tareq Mohammed, Hadia Kadhim Judran, et al.
Design of a 100 MW solar power plant on wetland in Bangladesh
Apu Kowsar, Sumon Chandra Debnath, et al.
Related Content
Continuous emotion recognition from facial expressions using CNN architecture
AIP Conf. Proc. (February 2024)
Real-time face emotion recognition for telediagnosis using machine learning
AIP Conf. Proc. (November 2023)
Facial and vocal expression-based comprehensive framework for real-time stress monitoring
AIP Conf. Proc. (August 2024)
Lecturer facial recognition system to automatically open the room and attendance
AIP Conf. Proc. (July 2024)
Development of coronary heart disease diagnosis system based on facial imagery
AIP Conf. Proc. (February 2024)