A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images

Tapotosh Ghosh; Md Hasan Al Banna; Md Jaber Al Nahian; M. Shamim Kaiser; Mufti Mahmud; Shaobao Li; Nelishia Pillay

doi:10.1007/978-3-031-24801-6_20

A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images

Tapotosh Ghosh^*, Md Hasan Al Banna, Md Jaber Al Nahian, M. Shamim Kaiser, Mufti Mahmud, Shaobao Li, Nelishia Pillay

^*Corresponding author for this work

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

16 Scopus citations

Abstract

Facial expression recognition is an intriguing research area that has been explored and utilized in a wide range of applications such as health, security, and human-computer interactions. The ability to recognize facial expressions accurately is crucial for human-computer interactions. However, most of the facial expression analysis techniques have so far paid little or no concern to users’ data privacy. To overcome this concern, in this paper, we incorporated Federated Learning (FL) as a privacy-preserving machine learning approach in the field of facial expression recognition to develop a shared model without exposing personal information. The individual models are trained on the different client devices where the data is stored. In this work, a lightweight Convolutional Neural Network (CNN) model called the MobileNet architecture is utilised to detect expressions from facial images. To evaluate the model, two publicly available datasets are used and several experiments are conducted. The result shows that the proposed privacy-preserving Federated-MobileNet approach could recognize facial expressions with considerable accuracy compared to the general approaches.

Original language	English
Title of host publication	Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings
Editors	Mufti Mahmud, Cosimo Ieracitano, Nadia Mammone, Francesco Carlo Morabito, M. Shamim Kaiser
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	277-292
Number of pages	16
ISBN (Print)	9783031248009
DOIs	https://doi.org/10.1007/978-3-031-24801-6_20
State	Published - 2022
Externally published	Yes
Event	2nd International Conference on Applied Intelligence and Informatics, AII 2022 - Reggio Calabria, Italy Duration: 1 Sep 2022 → 3 Sep 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1724 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	2nd International Conference on Applied Intelligence and Informatics, AII 2022
Country/Territory	Italy
City	Reggio Calabria
Period	1/09/22 → 3/09/22

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Emotion recognition
Facial expressions
Federated learning
Privacy-preserving

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-3-031-24801-6_20

Cite this

Ghosh, T., Banna, M. H. A., Nahian, M. J. A., Kaiser, M. S., Mahmud, M., Li, S., & Pillay, N. (2022). A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images. In M. Mahmud, C. Ieracitano, N. Mammone, F. C. Morabito, & M. S. Kaiser (Eds.), Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings (pp. 277-292). (Communications in Computer and Information Science; Vol. 1724 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-24801-6_20

Ghosh, Tapotosh ; Banna, Md Hasan Al ; Nahian, Md Jaber Al et al. / A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images. Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings. editor / Mufti Mahmud ; Cosimo Ieracitano ; Nadia Mammone ; Francesco Carlo Morabito ; M. Shamim Kaiser. Springer Science and Business Media Deutschland GmbH, 2022. pp. 277-292 (Communications in Computer and Information Science).

@inproceedings{146a17a081fe48389e5774c1829f37a0,

title = "A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images",

abstract = "Facial expression recognition is an intriguing research area that has been explored and utilized in a wide range of applications such as health, security, and human-computer interactions. The ability to recognize facial expressions accurately is crucial for human-computer interactions. However, most of the facial expression analysis techniques have so far paid little or no concern to users{\textquoteright} data privacy. To overcome this concern, in this paper, we incorporated Federated Learning (FL) as a privacy-preserving machine learning approach in the field of facial expression recognition to develop a shared model without exposing personal information. The individual models are trained on the different client devices where the data is stored. In this work, a lightweight Convolutional Neural Network (CNN) model called the MobileNet architecture is utilised to detect expressions from facial images. To evaluate the model, two publicly available datasets are used and several experiments are conducted. The result shows that the proposed privacy-preserving Federated-MobileNet approach could recognize facial expressions with considerable accuracy compared to the general approaches.",

keywords = "Emotion recognition, Facial expressions, Federated learning, Privacy-preserving",

author = "Tapotosh Ghosh and Banna, \{Md Hasan Al\} and Nahian, \{Md Jaber Al\} and Kaiser, \{M. Shamim\} and Mufti Mahmud and Shaobao Li and Nelishia Pillay",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 2nd International Conference on Applied Intelligence and Informatics, AII 2022 ; Conference date: 01-09-2022 Through 03-09-2022",

year = "2022",

doi = "10.1007/978-3-031-24801-6\_20",

language = "English",

isbn = "9783031248009",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "277--292",

editor = "Mufti Mahmud and Cosimo Ieracitano and Nadia Mammone and Morabito, \{Francesco Carlo\} and Kaiser, \{M. Shamim\}",

booktitle = "Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings",

address = "Germany",

}

Ghosh, T, Banna, MHA, Nahian, MJA, Kaiser, MS, Mahmud, M, Li, S & Pillay, N 2022, A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images. in M Mahmud, C Ieracitano, N Mammone, FC Morabito & MS Kaiser (eds), Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings. Communications in Computer and Information Science, vol. 1724 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 277-292, 2nd International Conference on Applied Intelligence and Informatics, AII 2022, Reggio Calabria, Italy, 1/09/22. https://doi.org/10.1007/978-3-031-24801-6_20

A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images. / Ghosh, Tapotosh; Banna, Md Hasan Al; Nahian, Md Jaber Al et al.
Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings. ed. / Mufti Mahmud; Cosimo Ieracitano; Nadia Mammone; Francesco Carlo Morabito; M. Shamim Kaiser. Springer Science and Business Media Deutschland GmbH, 2022. p. 277-292 (Communications in Computer and Information Science; Vol. 1724 CCIS).

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

TY - GEN

T1 - A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images

AU - Ghosh, Tapotosh

AU - Banna, Md Hasan Al

AU - Nahian, Md Jaber Al

AU - Kaiser, M. Shamim

AU - Mahmud, Mufti

AU - Li, Shaobao

AU - Pillay, Nelishia

PY - 2022

Y1 - 2022

N2 - Facial expression recognition is an intriguing research area that has been explored and utilized in a wide range of applications such as health, security, and human-computer interactions. The ability to recognize facial expressions accurately is crucial for human-computer interactions. However, most of the facial expression analysis techniques have so far paid little or no concern to users’ data privacy. To overcome this concern, in this paper, we incorporated Federated Learning (FL) as a privacy-preserving machine learning approach in the field of facial expression recognition to develop a shared model without exposing personal information. The individual models are trained on the different client devices where the data is stored. In this work, a lightweight Convolutional Neural Network (CNN) model called the MobileNet architecture is utilised to detect expressions from facial images. To evaluate the model, two publicly available datasets are used and several experiments are conducted. The result shows that the proposed privacy-preserving Federated-MobileNet approach could recognize facial expressions with considerable accuracy compared to the general approaches.

AB - Facial expression recognition is an intriguing research area that has been explored and utilized in a wide range of applications such as health, security, and human-computer interactions. The ability to recognize facial expressions accurately is crucial for human-computer interactions. However, most of the facial expression analysis techniques have so far paid little or no concern to users’ data privacy. To overcome this concern, in this paper, we incorporated Federated Learning (FL) as a privacy-preserving machine learning approach in the field of facial expression recognition to develop a shared model without exposing personal information. The individual models are trained on the different client devices where the data is stored. In this work, a lightweight Convolutional Neural Network (CNN) model called the MobileNet architecture is utilised to detect expressions from facial images. To evaluate the model, two publicly available datasets are used and several experiments are conducted. The result shows that the proposed privacy-preserving Federated-MobileNet approach could recognize facial expressions with considerable accuracy compared to the general approaches.

KW - Emotion recognition

KW - Facial expressions

KW - Federated learning

KW - Privacy-preserving

UR - https://www.scopus.com/pages/publications/85149649685

U2 - 10.1007/978-3-031-24801-6_20

DO - 10.1007/978-3-031-24801-6_20

M3 - Conference contribution

AN - SCOPUS:85149649685

SN - 9783031248009

T3 - Communications in Computer and Information Science

SP - 277

EP - 292

BT - Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings

A2 - Mahmud, Mufti

A2 - Ieracitano, Cosimo

A2 - Mammone, Nadia

A2 - Morabito, Francesco Carlo

A2 - Kaiser, M. Shamim

PB - Springer Science and Business Media Deutschland GmbH

T2 - 2nd International Conference on Applied Intelligence and Informatics, AII 2022

Y2 - 1 September 2022 through 3 September 2022

ER -

Ghosh T, Banna MHA, Nahian MJA, Kaiser MS, Mahmud M, Li S et al. A Privacy-Preserving Federated-MobileNet for Facial Expression Detection from Images. In Mahmud M, Ieracitano C, Mammone N, Morabito FC, Kaiser MS, editors, Applied Intelligence and Informatics - Second International Conference, AII 2022, Proceedings. Springer Science and Business Media Deutschland GmbH. 2022. p. 277-292. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-24801-6_20