Deep Facial Expression Recognition Using Transfer Learning and Fine-Tuning Techniques

Agobah, Harriet; Bamisile, Olusola; Cai, Dongsheng; Kulevome, Delanyo Kwame Bensah; Nimo, Benjamin Darkwa; Huang, Qi

doi:10.1109/ei256261.2022.10116540

Cited by 2 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Agobah et al 34 applied transfer learning using MobileNetV1 across multiple datasets for training, validation, and testing. They optimize CNN training by combining center loss and softmax loss, using the FER 2013 dataset for training and the JAFFE and CK + datasets for validation and testing.…”

Section: Related Workmentioning

confidence: 99%

“…While increasing the number of classes in the CK + dataset initially reduced accuracy due to complexity and data limitations, using a larger dataset significantly enhanced performance, raising accuracy by 4.41% over a smaller dataset. However, Agobah et al 34 highlighted that some misclassifications occurred due to the inherent complexity of distinguishing emotions like anger and sadness. 40 explored the use of CNN for sentiment identification on facial expression in the CK + and FER-2013 datasets.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

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

Agung,

Rifai,

Wijayanto

2024

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

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

Agung,

Rifai,

Wijayanto

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Thai-Viet Dang, A Secured, Multilevel Face Recognition based on Head Pose Estimation, MTCNN and FaceNet vertical axes. This image preprocessing will help the accuracy of face detection and recognition later [52][53][54][55][56][57][58].…”

Section: Head Pose Estimationmentioning

confidence: 99%

A Secured, Multilevel Face Recognition based on Head Pose Estimation, MTCNN and FaceNet

Dang,

Tran

2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Artificial Intelligence and IoT have always attracted a lot of attention from scholars and researchers because of their high applicability, which make them a typical technology of the Fourth Industrial Revolution. The hallmark of AI is its self-learning ability, which enables computers to predict and analyze complex data such as bio data (fingerprints, irises, and faces), voice recognition, text processing. Among those application, the face recognition is under intense research due to the demand in users’ identification. This paper proposes a new, secured, two-step solution for an identification system that uses MTCNN and FaceNet networks enhanced with head pose estimation of the users. The model's accuracy ranges from 92% to 95%, which make it competitive with recent research to demonstrate the system's usability.

show abstract

Deep Facial Expression Recognition Using Transfer Learning and Fine-Tuning Techniques

Cited by 2 publications

References 16 publications

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

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

A Secured, Multilevel Face Recognition based on Head Pose Estimation, MTCNN and FaceNet

Contact Info

Product

Resources

About