Facial Expression Recognition Using Deep Learning and Graph Convolution Networks

Deepak Parashar; Jinal Patel; Nilesh Bahadure; Rahul Joshi; Hetal Jethani; Bhoomi Shah

doi:10.1109/AIMLA63829.2025.11040280

Facial Expression Recognition Using Deep Learning and Graph Convolution Networks

Deepak Parashar^*
, Jinal Patel
, Nilesh Bahadure
, Rahul Joshi
, Hetal Jethani
, Bhoomi Shah

^*Corresponding author for this work

School of Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Facial expression recognition is an important for the cognitive psychology research and artificial intelligence. This study focuses on recognizing facial expressions in difficult situations like different angles of face, lighting, and partial face visibility. To analyze facial expression the Graph Convolution Network (GCN) method. This method first identifies the important areas from the video frames using a bottom-up attention module. These areas become nodes in a graph. This graph captures the connection between the nodes and whether the image's parts are related. Action units are highlighted using an attention map to find important details related to expression. The action map combines different parts of the face.

Original language	English
Title of host publication	Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications
Subtitle of host publication	Healthcare and Internet of Things, AIMLA 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331538972
DOIs	https://doi.org/10.1109/AIMLA63829.2025.11040280
Publication status	Published - 2025
Event	3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025 - Namakkal, India Duration: 29-04-2025 → 30-04-2025

Publication series

Name	Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025

Conference

Conference	3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025
Country/Territory	India
City	Namakkal
Period	29-04-25 → 30-04-25

All Science Journal Classification (ASJC) codes

Instrumentation
Modelling and Simulation
Artificial Intelligence
Computer Science Applications
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/AIMLA63829.2025.11040280

Cite this

Parashar, D., Patel, J., Bahadure, N., Joshi, R., Jethani, H., & Shah, B. (2025). Facial Expression Recognition Using Deep Learning and Graph Convolution Networks. In Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025 (Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AIMLA63829.2025.11040280

Parashar, Deepak ; Patel, Jinal ; Bahadure, Nilesh et al. / Facial Expression Recognition Using Deep Learning and Graph Convolution Networks. Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025).

@inproceedings{f8426dc45bff4e79886121f3fbba1c96,

title = "Facial Expression Recognition Using Deep Learning and Graph Convolution Networks",

abstract = "Facial expression recognition is an important for the cognitive psychology research and artificial intelligence. This study focuses on recognizing facial expressions in difficult situations like different angles of face, lighting, and partial face visibility. To analyze facial expression the Graph Convolution Network (GCN) method. This method first identifies the important areas from the video frames using a bottom-up attention module. These areas become nodes in a graph. This graph captures the connection between the nodes and whether the image's parts are related. Action units are highlighted using an attention map to find important details related to expression. The action map combines different parts of the face.",

author = "Deepak Parashar and Jinal Patel and Nilesh Bahadure and Rahul Joshi and Hetal Jethani and Bhoomi Shah",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025 ; Conference date: 29-04-2025 Through 30-04-2025",

year = "2025",

doi = "10.1109/AIMLA63829.2025.11040280",

language = "English",

series = "Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications",

address = "United States",

}

Parashar, D, Patel, J, Bahadure, N, Joshi, R, Jethani, H & Shah, B 2025, Facial Expression Recognition Using Deep Learning and Graph Convolution Networks. in Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025. Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025, Institute of Electrical and Electronics Engineers Inc., 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025, Namakkal, India, 29-04-25. https://doi.org/10.1109/AIMLA63829.2025.11040280

Facial Expression Recognition Using Deep Learning and Graph Convolution Networks. / Parashar, Deepak; Patel, Jinal; Bahadure, Nilesh et al.
Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025. Institute of Electrical and Electronics Engineers Inc., 2025. (Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Facial Expression Recognition Using Deep Learning and Graph Convolution Networks

AU - Parashar, Deepak

AU - Patel, Jinal

AU - Bahadure, Nilesh

AU - Joshi, Rahul

AU - Jethani, Hetal

AU - Shah, Bhoomi

PY - 2025

Y1 - 2025

N2 - Facial expression recognition is an important for the cognitive psychology research and artificial intelligence. This study focuses on recognizing facial expressions in difficult situations like different angles of face, lighting, and partial face visibility. To analyze facial expression the Graph Convolution Network (GCN) method. This method first identifies the important areas from the video frames using a bottom-up attention module. These areas become nodes in a graph. This graph captures the connection between the nodes and whether the image's parts are related. Action units are highlighted using an attention map to find important details related to expression. The action map combines different parts of the face.

AB - Facial expression recognition is an important for the cognitive psychology research and artificial intelligence. This study focuses on recognizing facial expressions in difficult situations like different angles of face, lighting, and partial face visibility. To analyze facial expression the Graph Convolution Network (GCN) method. This method first identifies the important areas from the video frames using a bottom-up attention module. These areas become nodes in a graph. This graph captures the connection between the nodes and whether the image's parts are related. Action units are highlighted using an attention map to find important details related to expression. The action map combines different parts of the face.

UR - https://www.scopus.com/pages/publications/105010566833

UR - https://www.scopus.com/pages/publications/105010566833#tab=citedBy

U2 - 10.1109/AIMLA63829.2025.11040280

DO - 10.1109/AIMLA63829.2025.11040280

M3 - Conference contribution

AN - SCOPUS:105010566833

T3 - Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025

BT - Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025

Y2 - 29 April 2025 through 30 April 2025

ER -

Parashar D, Patel J, Bahadure N, Joshi R, Jethani H, Shah B. Facial Expression Recognition Using Deep Learning and Graph Convolution Networks. In Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025. Institute of Electrical and Electronics Engineers Inc. 2025. (Proceedings - 3rd International Conference on Artificial Intelligence and Machine Learning Applications: Healthcare and Internet of Things, AIMLA 2025). doi: 10.1109/AIMLA63829.2025.11040280

Facial Expression Recognition Using Deep Learning and Graph Convolution Networks

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this