Facial expression recognition using lightweight deep learning modeling

Mubashir Ahmad; Saira; Omar Alfandi; Asad Masood Khattak; Syed Furqan Qadri; Iftikhar Ahmed Saeed; Salabat Khan; Bashir Hayat; Arshad Ahmad

doi:10.3934/mbe.2023357

Facial expression recognition using lightweight deep learning modeling

Mubashir Ahmad^*, Saira, Omar Alfandi, Asad Masood Khattak^*, Syed Furqan Qadri^*, Iftikhar Ahmed Saeed, Salabat Khan, Bashir Hayat, Arshad Ahmad

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

Facial expression is a type of communication and is useful in many areas of computer vision, including intelligent visual surveillance, human-robot interaction and human behavior analysis. A deep learning approach is presented to classify happy, sad, angry, fearful, contemptuous, surprised and disgusted expressions. Accurate detection and classification of human facial expression is a critical task in image processing due to the inconsistencies amid the complexity, including change in illumination, occlusion, noise and the over-fitting problem. A stacked sparse auto-encoder for facial expression recognition (SSAE-FER) is used for unsupervised pre-training and supervised fine-tuning. SSAE-FER automatically extracts features from input images, and the softmax classifier is used to classify the expressions. Our method achieved an accuracy of 92.50% on the JAFFE dataset and 99.30% on the CK+ dataset. SSAE-FER performs well compared to the other comparative methods in the same domain.

Original language	English
Pages (from-to)	8208-8225
Number of pages	18
Journal	Mathematical Biosciences and Engineering
Volume	20
Issue number	5
DOIs	https://doi.org/10.3934/mbe.2023357
State	Published - 2023
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0).

Keywords

classification
deep learning
facial expression recognition
machine learning
stacked sparse auto-encoder

ASJC Scopus subject areas

Modeling and Simulation
General Agricultural and Biological Sciences
Computational Mathematics
Applied Mathematics

Access to Document

10.3934/mbe.2023357

Cite this

@article{663db52e44c34f0a83d4a63d27cc78dd,

title = "Facial expression recognition using lightweight deep learning modeling",

abstract = "Facial expression is a type of communication and is useful in many areas of computer vision, including intelligent visual surveillance, human-robot interaction and human behavior analysis. A deep learning approach is presented to classify happy, sad, angry, fearful, contemptuous, surprised and disgusted expressions. Accurate detection and classification of human facial expression is a critical task in image processing due to the inconsistencies amid the complexity, including change in illumination, occlusion, noise and the over-fitting problem. A stacked sparse auto-encoder for facial expression recognition (SSAE-FER) is used for unsupervised pre-training and supervised fine-tuning. SSAE-FER automatically extracts features from input images, and the softmax classifier is used to classify the expressions. Our method achieved an accuracy of 92.50\% on the JAFFE dataset and 99.30\% on the CK+ dataset. SSAE-FER performs well compared to the other comparative methods in the same domain.",

keywords = "classification, deep learning, facial expression recognition, machine learning, stacked sparse auto-encoder",

author = "Mubashir Ahmad and Saira and Omar Alfandi and Khattak, \{Asad Masood\} and Qadri, \{Syed Furqan\} and Saeed, \{Iftikhar Ahmed\} and Salabat Khan and Bashir Hayat and Arshad Ahmad",

note = "Publisher Copyright: {\textcopyright} 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0).",

year = "2023",

doi = "10.3934/mbe.2023357",

language = "English",

volume = "20",

pages = "8208--8225",

journal = "Mathematical Biosciences and Engineering",

issn = "1547-1063",

publisher = "American Institute of Mathematical Sciences",

number = "5",

}

TY - JOUR

T1 - Facial expression recognition using lightweight deep learning modeling

AU - Ahmad, Mubashir

AU - Saira,

AU - Alfandi, Omar

AU - Khattak, Asad Masood

AU - Qadri, Syed Furqan

AU - Saeed, Iftikhar Ahmed

AU - Khan, Salabat

AU - Hayat, Bashir

AU - Ahmad, Arshad

N1 - Publisher Copyright: © 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0).

PY - 2023

Y1 - 2023

N2 - Facial expression is a type of communication and is useful in many areas of computer vision, including intelligent visual surveillance, human-robot interaction and human behavior analysis. A deep learning approach is presented to classify happy, sad, angry, fearful, contemptuous, surprised and disgusted expressions. Accurate detection and classification of human facial expression is a critical task in image processing due to the inconsistencies amid the complexity, including change in illumination, occlusion, noise and the over-fitting problem. A stacked sparse auto-encoder for facial expression recognition (SSAE-FER) is used for unsupervised pre-training and supervised fine-tuning. SSAE-FER automatically extracts features from input images, and the softmax classifier is used to classify the expressions. Our method achieved an accuracy of 92.50% on the JAFFE dataset and 99.30% on the CK+ dataset. SSAE-FER performs well compared to the other comparative methods in the same domain.

AB - Facial expression is a type of communication and is useful in many areas of computer vision, including intelligent visual surveillance, human-robot interaction and human behavior analysis. A deep learning approach is presented to classify happy, sad, angry, fearful, contemptuous, surprised and disgusted expressions. Accurate detection and classification of human facial expression is a critical task in image processing due to the inconsistencies amid the complexity, including change in illumination, occlusion, noise and the over-fitting problem. A stacked sparse auto-encoder for facial expression recognition (SSAE-FER) is used for unsupervised pre-training and supervised fine-tuning. SSAE-FER automatically extracts features from input images, and the softmax classifier is used to classify the expressions. Our method achieved an accuracy of 92.50% on the JAFFE dataset and 99.30% on the CK+ dataset. SSAE-FER performs well compared to the other comparative methods in the same domain.

KW - classification

KW - deep learning

KW - facial expression recognition

KW - machine learning

KW - stacked sparse auto-encoder

UR - http://www.scopus.com/inward/record.url?scp=85150339087&partnerID=8YFLogxK

U2 - 10.3934/mbe.2023357

DO - 10.3934/mbe.2023357

M3 - Article

C2 - 37161193

AN - SCOPUS:85150339087

SN - 1547-1063

VL - 20

SP - 8208

EP - 8225

JO - Mathematical Biosciences and Engineering

JF - Mathematical Biosciences and Engineering

IS - 5

ER -

Facial expression recognition using lightweight deep learning modeling

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this