Improving Human Emotion Recognition from Emotive Videos Using Geometric Data Augmentation

Nusrat J Shoumy; Li-Minn Ang; D. M. Motiur Rahaman; Tanveer Zia; Kah Phooi Seng; Sabira Khatun

doi:10.1007/978-3-030-79463-7_13

Back

Improving Human Emotion Recognition from Emotive Videos Using Geometric Data Augmentation

Conference paper

Peer reviewed

Improving Human Emotion Recognition from Emotive Videos Using Geometric Data Augmentation

Nusrat J Shoumy, Li-Minn Ang, D. M. Motiur Rahaman, Tanveer Zia, Kah Phooi Seng and Sabira Khatun

Advances and Trends in Artificial Intelligence. From Theory to Practice, pp.149-161

International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 34th (Kuala Lumpur, Malaysia, 26-Jul-2021 - 29-Jul-2021)

Lecture Notes in Computer Science, 12799, Springer International Publishing

2021

DOI: https://doi.org/10.1007/978-3-030-79463-7_13

Files and links (1)

url

https://doi.org/10.1007/978-3-030-79463-7_13View

Published Version

Abstract

Data augmentation

Data classification

Emotion recognition

Multimodal data

Neural network

Emotional recognition from videos or images requires large amount of data to obtain high performance and classification accuracy. However, large datasets are not always easily available. A good solution to this problem is to augment the data and extrapolate it to create a bigger dataset for training the classifier. In this paper, we evaluate the impact of different geometric data augmentation (GDA) techniques on emotion recognition accuracy using facial image data. The GDA techniques that were implemented were horizontal reflection, cropping, rotation separately and combined. In addition to this, our system was further evaluated with four different classifiers (Convolutional Neural Network (CNN), Linear Discriminant Analysis (LDA), K-Nearest Neighbor (kNN) and Decision Tree (DT)) to determine which of the four classifiers achieves the best results. In the proposed system, we used augmented data from a dataset (SAVEE) to perform training, and testing was carried out by the original data. A combination of GDA techniques using the CNN classifier was found to give the best performance of approximately 97.8%. Our system with GDA augmentation was shown to outperform previous approaches where only the original dataset was used for classifier training.

Details

Title: Improving Human Emotion Recognition from Emotive Videos Using Geometric Data Augmentation
Authors: Nusrat J Shoumy (Corresponding Author) - Charles Sturt University
Li-Minn Ang (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
D. M. Motiur Rahaman (Author) - Charles Sturt University
Tanveer Zia (Author) - Charles Sturt University
Kah Phooi Seng (Author) - UNSW Australia
Sabira Khatun (Author) - Universiti Malaysia Pahang
Publication details: Advances and Trends in Artificial Intelligence. From Theory to Practice, pp.149-161
Conference details: International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 34th (Kuala Lumpur, Malaysia, 26-Jul-2021 - 29-Jul-2021)
Series: Lecture Notes in Computer Science; 12799
Publisher: Springer International Publishing
DOI: 10.1007/978-3-030-79463-7_13; 10.1007/978-3-030-79463-7
ISSN: 1611-3349; 1611-3349
ISBN: 9783030794637
Organisation Unit: School of Science, Technology and Engineering; University of the Sunshine Coast, Queensland; Engage Research Lab
Language: English
Record Identifier: 99571605502621
Output Type: Conference paper

Metrics

11 Record Views