The Impact of Eyebrows Region on Deep Face Recognition

Nova Hadi Lestriandoko; Luuk Spreeuwers; Raymond Veldhuis

doi:10.1109/IC3INA60834.2023.10285734

The Impact of Eyebrows Region on Deep Face Recognition

Nova Hadi Lestriandoko^*, Luuk Spreeuwers, Raymond Veldhuis

^*Corresponding author for this work

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

124 Downloads (Pure)

Abstract

We investigate the importance of the information contained in the area of the eyebrows for deep face recognition. An isotropic 2D Gaussian low-pass filter of varying bandwidth is used to remove discriminative information in the probe and reference images gradually. We measure the recognition performance of two deep learning-based face recognition systems as a function of the bandwidth of the low-pass filter applied to the eyebrows. Methods are tested on the frontal face and high-resolution images from the PUT database. The results showed that even though the eyebrows are important for recognition, deep learning still works well on facial images with removed eyebrows. Furthermore, we found that the discriminative information provided by eyebrows comes from their shapes, not their textures.

Original language	English
Title of host publication	2023 10th International Conference on Computer, Control, Informatics and its Applications
Subtitle of host publication	Exploring the Power of Data: Leveraging Information to Drive Digital Innovation, IC3INA 2023
Publisher	IEEE
Pages	319-323
Number of pages	5
ISBN (Electronic)	9798350394870
DOIs	https://doi.org/10.1109/IC3INA60834.2023.10285734
Publication status	Published - 18 Oct 2023
Event	10th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2023: Exploring the Power of Data: Leveraging Information to Drive Digital Innovation - Virtual, Online, Indonesia Duration: 4 Oct 2023 → 5 Oct 2023 Conference number: 10

Conference

Conference	10th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2023
Abbreviated title	IC3INA 2023
Country/Territory	Indonesia
City	Virtual, Online
Period	4/10/23 → 5/10/23

Keywords

biometrics
deep learning
eyebrows
facial recognition
Gaussian blur
masking
2023 OA procedure

Access to Document

10.1109/IC3INA60834.2023.10285734

The_Impact_of_Eyebrows_Region_on_Deep_Face_RecognitionFinal published version, 446 KBLicence: Taverne

Cite this

Lestriandoko, N. H., Spreeuwers, L., & Veldhuis, R. (2023). The Impact of Eyebrows Region on Deep Face Recognition. In 2023 10th International Conference on Computer, Control, Informatics and its Applications: Exploring the Power of Data: Leveraging Information to Drive Digital Innovation, IC3INA 2023 (pp. 319-323). IEEE. https://doi.org/10.1109/IC3INA60834.2023.10285734

@inproceedings{ca64f8d4ca4448e9b6e60523c48f66ec,

title = "The Impact of Eyebrows Region on Deep Face Recognition",

abstract = "We investigate the importance of the information contained in the area of the eyebrows for deep face recognition. An isotropic 2D Gaussian low-pass filter of varying bandwidth is used to remove discriminative information in the probe and reference images gradually. We measure the recognition performance of two deep learning-based face recognition systems as a function of the bandwidth of the low-pass filter applied to the eyebrows. Methods are tested on the frontal face and high-resolution images from the PUT database. The results showed that even though the eyebrows are important for recognition, deep learning still works well on facial images with removed eyebrows. Furthermore, we found that the discriminative information provided by eyebrows comes from their shapes, not their textures.",

keywords = "biometrics, deep learning, eyebrows, facial recognition, Gaussian blur, masking, 2023 OA procedure",

author = "Lestriandoko, {Nova Hadi} and Luuk Spreeuwers and Raymond Veldhuis",

note = "Funding Information: The research described in this paper was supported by the Research and Innovation in Science and Technology Project (RISET-Pro) of the Ministry of Research, Technology, and Higher Education of the Republic Indonesia (World Bank Loan No.8245-ID) and National Research and Innovation Agency (BRIN). Publisher Copyright: {\textcopyright} 2023 IEEE.; 10th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2023 : Exploring the Power of Data: Leveraging Information to Drive Digital Innovation, IC3INA 2023 ; Conference date: 04-10-2023 Through 05-10-2023",

year = "2023",

month = oct,

day = "18",

doi = "10.1109/IC3INA60834.2023.10285734",

language = "English",

pages = "319--323",

booktitle = "2023 10th International Conference on Computer, Control, Informatics and its Applications",

publisher = "IEEE",

address = "United States",

}

Lestriandoko, NH, Spreeuwers, L & Veldhuis, R 2023, The Impact of Eyebrows Region on Deep Face Recognition. in 2023 10th International Conference on Computer, Control, Informatics and its Applications: Exploring the Power of Data: Leveraging Information to Drive Digital Innovation, IC3INA 2023. IEEE, pp. 319-323, 10th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2023, Virtual, Online, Indonesia, 4/10/23. https://doi.org/10.1109/IC3INA60834.2023.10285734

The Impact of Eyebrows Region on Deep Face Recognition. / Lestriandoko, Nova Hadi; Spreeuwers, Luuk ; Veldhuis, Raymond.
2023 10th International Conference on Computer, Control, Informatics and its Applications: Exploring the Power of Data: Leveraging Information to Drive Digital Innovation, IC3INA 2023. IEEE, 2023. p. 319-323.

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

TY - GEN

T1 - The Impact of Eyebrows Region on Deep Face Recognition

AU - Lestriandoko, Nova Hadi

AU - Spreeuwers, Luuk

AU - Veldhuis, Raymond

N1 - Conference code: 10

PY - 2023/10/18

Y1 - 2023/10/18

N2 - We investigate the importance of the information contained in the area of the eyebrows for deep face recognition. An isotropic 2D Gaussian low-pass filter of varying bandwidth is used to remove discriminative information in the probe and reference images gradually. We measure the recognition performance of two deep learning-based face recognition systems as a function of the bandwidth of the low-pass filter applied to the eyebrows. Methods are tested on the frontal face and high-resolution images from the PUT database. The results showed that even though the eyebrows are important for recognition, deep learning still works well on facial images with removed eyebrows. Furthermore, we found that the discriminative information provided by eyebrows comes from their shapes, not their textures.

AB - We investigate the importance of the information contained in the area of the eyebrows for deep face recognition. An isotropic 2D Gaussian low-pass filter of varying bandwidth is used to remove discriminative information in the probe and reference images gradually. We measure the recognition performance of two deep learning-based face recognition systems as a function of the bandwidth of the low-pass filter applied to the eyebrows. Methods are tested on the frontal face and high-resolution images from the PUT database. The results showed that even though the eyebrows are important for recognition, deep learning still works well on facial images with removed eyebrows. Furthermore, we found that the discriminative information provided by eyebrows comes from their shapes, not their textures.

KW - biometrics

KW - deep learning

KW - eyebrows

KW - facial recognition

KW - Gaussian blur

KW - masking

KW - 2023 OA procedure

UR - http://www.scopus.com/inward/record.url?scp=85175983360&partnerID=8YFLogxK

U2 - 10.1109/IC3INA60834.2023.10285734

DO - 10.1109/IC3INA60834.2023.10285734

M3 - Conference contribution

AN - SCOPUS:85175983360

SP - 319

EP - 323

BT - 2023 10th International Conference on Computer, Control, Informatics and its Applications

PB - IEEE

T2 - 10th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2023

Y2 - 4 October 2023 through 5 October 2023

ER -

The Impact of Eyebrows Region on Deep Face Recognition

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this