Image-based facial emotion recognition using convolutional neural network on emognition dataset

Agung, Erlangga Satrio and Rifai, Achmad Pratama and Wijayanto, Titis (2024) Image-based facial emotion recognition using convolutional neural network on emognition dataset. Scientific Reports, 14 (1): 14429. ISSN 20452322

[thumbnail of Detecting emotions from facial images is difcult because facial expressions can vary signifcantly. Previous research on using deep learning models to classify emotions from facial images has been carried out on various datasets that contain a limited rang] Text (Detecting emotions from facial images is difcult because facial expressions can vary signifcantly. Previous research on using deep learning models to classify emotions from facial images has been carried out on various datasets that contain a limited rang)
Image-based facial emotion recognition using convolutional neural network on emognition dataset.pdf - Published Version
Restricted to Registered users only

Download (4MB) | Request a copy

Abstract

Detecting emotions from facial images is difficult because facial expressions can vary significantly. Previous research on using deep learning models to classify emotions from facial images has been carried out on various datasets that contain a limited range of expressions. This study expands the use of deep learning for facial emotion recognition (FER) based on Emognition dataset that includes ten target emotions: amusement, awe, enthusiasm, liking, surprise, anger, disgust, fear, sadness, and neutral. A series of data preprocessing was carried out to convert video data into images and augment the data. This study proposes Convolutional Neural Network (CNN) models built through two approaches, which are transfer learning (fine-tuned) with pre-trained models of Inception-V3 and MobileNet-V2 and building from scratch using the Taguchi method to find robust combination of hyperparameters setting. The proposed model demonstrated favorable performance over a series of experimental processes with an accuracy and an average F1-score of 96 and 0.95, respectively, on the test data. © The Author(s) 2024.

Item Type: Article
Additional Information: Cited by: 5; All Open Access, Gold Open Access
Uncontrolled Keywords: Facial emotion recognition, Convolutional neural network, Deep learning, Emognition dataset
Subjects: T Technology > TJ Mechanical engineering and machinery
Divisions: Faculty of Engineering > Mechanical and Industrial Engineering Department
Depositing User: Yulistiarini Kumaraningrum KUMARANINGRUM
Date Deposited: 05 Nov 2024 03:13
Last Modified: 05 Nov 2024 03:13
URI: https://ir.lib.ugm.ac.id/id/eprint/10705

Actions (login required)

View Item
View Item