Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study

Nehal Al-Otaiby; El Sayed M. El-Alfy

doi:10.1109/ICCIT58132.2023.10273970

Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study

Nehal Al-Otaiby^*
, El Sayed M. El-Alfy

^*Corresponding author for this work

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

2 Scopus citations

Abstract

Vision Transformers have been recently introduced and achieved great success in the last two years beating convolutional neural networks (CNN) in many computer vision applications including Face Transformer for face recognition. However, one of the rising concerns is how sensitive these models are to various types of image degradations, especially when used for biometric authentication and person identification. This research aims at reviewing related work and presenting a case study to investigate the robustness of a fine-tuned version of Face Transformer under different pose, age, and gender variations for several degradations such as noise, blur, and resolution reduction. Several experiments have been conducted to train and test the model using two benchmark datasets (VGGFace2 and LFW) and benchmark its performance with FaceNet.

Original language	English
Title of host publication	2023 3rd International Conference on Computing and Information Technology, ICCIT 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	409-415
Number of pages	7
ISBN (Electronic)	9798350321487
DOIs	https://doi.org/10.1109/ICCIT58132.2023.10273970
State	Published - 2023
Event	3rd International Conference on Computing and Information Technology, ICCIT 2023 - Tabuk, Saudi Arabia Duration: 13 Sep 2023 → 14 Sep 2023

Publication series

Name	2023 3rd International Conference on Computing and Information Technology, ICCIT 2023

Conference

Conference	3rd International Conference on Computing and Information Technology, ICCIT 2023
Country/Territory	Saudi Arabia
City	Tabuk
Period	13/09/23 → 14/09/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Deep learning
biometric authentication
face recognition
vision transformer

ASJC Scopus subject areas

Electrical and Electronic Engineering
Mechanical Engineering
Energy Engineering and Power Technology

Access to Document

10.1109/ICCIT58132.2023.10273970

Cite this

Al-Otaiby, N., & El-Alfy, E. S. M. (2023). Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study. In 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023 (pp. 409-415). (2023 3rd International Conference on Computing and Information Technology, ICCIT 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCIT58132.2023.10273970

Al-Otaiby, Nehal ; El-Alfy, El Sayed M. / Effects of Face Image Degradation on Recognition with Vision Transformers : Review and Case Study. 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 409-415 (2023 3rd International Conference on Computing and Information Technology, ICCIT 2023).

@inproceedings{add1ffdc6d0b42b9913862a8346926ce,

title = "Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study",

abstract = "Vision Transformers have been recently introduced and achieved great success in the last two years beating convolutional neural networks (CNN) in many computer vision applications including Face Transformer for face recognition. However, one of the rising concerns is how sensitive these models are to various types of image degradations, especially when used for biometric authentication and person identification. This research aims at reviewing related work and presenting a case study to investigate the robustness of a fine-tuned version of Face Transformer under different pose, age, and gender variations for several degradations such as noise, blur, and resolution reduction. Several experiments have been conducted to train and test the model using two benchmark datasets (VGGFace2 and LFW) and benchmark its performance with FaceNet.",

keywords = "Deep learning, biometric authentication, face recognition, vision transformer",

author = "Nehal Al-Otaiby and El-Alfy, \{El Sayed M.\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 3rd International Conference on Computing and Information Technology, ICCIT 2023 ; Conference date: 13-09-2023 Through 14-09-2023",

year = "2023",

doi = "10.1109/ICCIT58132.2023.10273970",

language = "English",

series = "2023 3rd International Conference on Computing and Information Technology, ICCIT 2023",

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

pages = "409--415",

booktitle = "2023 3rd International Conference on Computing and Information Technology, ICCIT 2023",

address = "United States",

}

Al-Otaiby, N & El-Alfy, ESM 2023, Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study. in 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023. 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023, Institute of Electrical and Electronics Engineers Inc., pp. 409-415, 3rd International Conference on Computing and Information Technology, ICCIT 2023, Tabuk, Saudi Arabia, 13/09/23. https://doi.org/10.1109/ICCIT58132.2023.10273970

Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study. / Al-Otaiby, Nehal; El-Alfy, El Sayed M.
2023 3rd International Conference on Computing and Information Technology, ICCIT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 409-415 (2023 3rd International Conference on Computing and Information Technology, ICCIT 2023).

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

TY - GEN

T1 - Effects of Face Image Degradation on Recognition with Vision Transformers

T2 - 3rd International Conference on Computing and Information Technology, ICCIT 2023

AU - Al-Otaiby, Nehal

AU - El-Alfy, El Sayed M.

PY - 2023

Y1 - 2023

N2 - Vision Transformers have been recently introduced and achieved great success in the last two years beating convolutional neural networks (CNN) in many computer vision applications including Face Transformer for face recognition. However, one of the rising concerns is how sensitive these models are to various types of image degradations, especially when used for biometric authentication and person identification. This research aims at reviewing related work and presenting a case study to investigate the robustness of a fine-tuned version of Face Transformer under different pose, age, and gender variations for several degradations such as noise, blur, and resolution reduction. Several experiments have been conducted to train and test the model using two benchmark datasets (VGGFace2 and LFW) and benchmark its performance with FaceNet.

AB - Vision Transformers have been recently introduced and achieved great success in the last two years beating convolutional neural networks (CNN) in many computer vision applications including Face Transformer for face recognition. However, one of the rising concerns is how sensitive these models are to various types of image degradations, especially when used for biometric authentication and person identification. This research aims at reviewing related work and presenting a case study to investigate the robustness of a fine-tuned version of Face Transformer under different pose, age, and gender variations for several degradations such as noise, blur, and resolution reduction. Several experiments have been conducted to train and test the model using two benchmark datasets (VGGFace2 and LFW) and benchmark its performance with FaceNet.

KW - Deep learning

KW - biometric authentication

KW - face recognition

KW - vision transformer

UR - https://www.scopus.com/pages/publications/85175436979

U2 - 10.1109/ICCIT58132.2023.10273970

DO - 10.1109/ICCIT58132.2023.10273970

M3 - Conference contribution

AN - SCOPUS:85175436979

T3 - 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023

SP - 409

EP - 415

BT - 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 September 2023 through 14 September 2023

ER -

Al-Otaiby N, El-Alfy ESM. Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study. In 2023 3rd International Conference on Computing and Information Technology, ICCIT 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 409-415. (2023 3rd International Conference on Computing and Information Technology, ICCIT 2023). doi: 10.1109/ICCIT58132.2023.10273970

Effects of Face Image Degradation on Recognition with Vision Transformers: Review and Case Study

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this