Abstract | ||
---|---|---|
This paper outlines the effectiveness of several popular machine learning algorithms for facial expression recognition. The dataset used for this paper consists of 35887 images of size 48x48 pixels which are all depicting faces posed in one of seven expressions (anger, disgust, fear, happy, sad, surprise, neutral). This is a popularly used dataset for practice and exploration and there are many different approaches suggested in the literature. In this paper, the following algorithms are applied and tested: AdaBoost, Logistic Regression, Dense Neural Network (DNN), and Convolutional Neural Network (CNN). CNN is shown to provide the highest accuracy compared to other algorithms. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/EIT48999.2020.9208316 | 2020 IEEE International Conference on Electro Information Technology (EIT) |
Keywords | DocType | ISSN |
convolutional neural network,emotion recognition,machine learning,facial expression recognition,FER2013,Kaggle,adaboost | Conference | 2154-0357 |
ISBN | Citations | PageRank |
978-1-7281-5317-9 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seth Gory | 1 | 0 | 0.34 |
Mahmood A. Al-Khassaweneh | 2 | 1 | 3.07 |
Piotr Szczurek | 3 | 0 | 0.34 |