Deep Learning-Based Facial Landmarks Localization with Loss Comparison

Savina Colaco; Dong Seog Han

doi:10.1109/ICTC49870.2020.9289429

Deep Learning-Based Facial Landmarks Localization with Loss Comparison

Savina Colaco
, Dong Seog Han

School of Electronics Engineering

Kyungpook National University

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

1 Scopus citations

Abstract

Facial landmarks localization has widespread use in various facial analysis applications which can solve major problems in the computer vision field. Localizing the key points such as eye corners, eye centers, nose center, jawline, etc gives the vital information needed for analysis of face status like expressions, health conditions, etc. The paper addresses a deep learning-based facial landmarks localization approach. MobileNet V3 is used to predict the facial landmarks on human faces which are mapped on the detected face in real-time. The model is evaluated with the wing and adaptive wing loss functions. The detector is examined with various head poses and occlusion conditions.

Original language	English
Title of host publication	ICTC 2020 - 11th International Conference on ICT Convergence
Subtitle of host publication	Data, Network, and AI in the Age of Untact
Publisher	IEEE Computer Society
Pages	584-587
Number of pages	4
ISBN (Electronic)	9781728167589
DOIs	https://doi.org/10.1109/ICTC49870.2020.9289429
State	Published - 21 Oct 2020
Event	11th International Conference on Information and Communication Technology Convergence, ICTC 2020 - Jeju Island, Korea, Republic of Duration: 21 Oct 2020 → 23 Oct 2020

Publication series

Name	International Conference on ICT Convergence
Volume	2020-October
ISSN (Print)	2162-1233
ISSN (Electronic)	2162-1241

Conference

Conference	11th International Conference on Information and Communication Technology Convergence, ICTC 2020
Country/Territory	Korea, Republic of
City	Jeju Island
Period	21/10/20 → 23/10/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Adaptive wing loss
Facial landmarks
Facial landmarks localization
MobileNet
Wing loss

Access to Document

10.1109/ICTC49870.2020.9289429

Cite this

Colaco, S., & Han, D. S. (2020). Deep Learning-Based Facial Landmarks Localization with Loss Comparison. In ICTC 2020 - 11th International Conference on ICT Convergence: Data, Network, and AI in the Age of Untact (pp. 584-587). Article 9289429 (International Conference on ICT Convergence; Vol. 2020-October). IEEE Computer Society. https://doi.org/10.1109/ICTC49870.2020.9289429

@inproceedings{71cbf55a574b4576a3b8990452512a5f,

title = "Deep Learning-Based Facial Landmarks Localization with Loss Comparison",

abstract = "Facial landmarks localization has widespread use in various facial analysis applications which can solve major problems in the computer vision field. Localizing the key points such as eye corners, eye centers, nose center, jawline, etc gives the vital information needed for analysis of face status like expressions, health conditions, etc. The paper addresses a deep learning-based facial landmarks localization approach. MobileNet V3 is used to predict the facial landmarks on human faces which are mapped on the detected face in real-time. The model is evaluated with the wing and adaptive wing loss functions. The detector is examined with various head poses and occlusion conditions.",

keywords = "Adaptive wing loss, Facial landmarks, Facial landmarks localization, MobileNet, Wing loss",

author = "Savina Colaco and Han, \{Dong Seog\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 11th International Conference on Information and Communication Technology Convergence, ICTC 2020 ; Conference date: 21-10-2020 Through 23-10-2020",

year = "2020",

month = oct,

day = "21",

doi = "10.1109/ICTC49870.2020.9289429",

language = "English",

series = "International Conference on ICT Convergence",

publisher = "IEEE Computer Society",

pages = "584--587",

booktitle = "ICTC 2020 - 11th International Conference on ICT Convergence",

address = "United States",

}

Colaco, S & Han, DS 2020, Deep Learning-Based Facial Landmarks Localization with Loss Comparison. in ICTC 2020 - 11th International Conference on ICT Convergence: Data, Network, and AI in the Age of Untact., 9289429, International Conference on ICT Convergence, vol. 2020-October, IEEE Computer Society, pp. 584-587, 11th International Conference on Information and Communication Technology Convergence, ICTC 2020, Jeju Island, Korea, Republic of, 21/10/20. https://doi.org/10.1109/ICTC49870.2020.9289429

Deep Learning-Based Facial Landmarks Localization with Loss Comparison. / Colaco, Savina; Han, Dong Seog.
ICTC 2020 - 11th International Conference on ICT Convergence: Data, Network, and AI in the Age of Untact. IEEE Computer Society, 2020. p. 584-587 9289429 (International Conference on ICT Convergence; Vol. 2020-October).

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

TY - GEN

T1 - Deep Learning-Based Facial Landmarks Localization with Loss Comparison

AU - Colaco, Savina

AU - Han, Dong Seog

PY - 2020/10/21

Y1 - 2020/10/21

N2 - Facial landmarks localization has widespread use in various facial analysis applications which can solve major problems in the computer vision field. Localizing the key points such as eye corners, eye centers, nose center, jawline, etc gives the vital information needed for analysis of face status like expressions, health conditions, etc. The paper addresses a deep learning-based facial landmarks localization approach. MobileNet V3 is used to predict the facial landmarks on human faces which are mapped on the detected face in real-time. The model is evaluated with the wing and adaptive wing loss functions. The detector is examined with various head poses and occlusion conditions.

AB - Facial landmarks localization has widespread use in various facial analysis applications which can solve major problems in the computer vision field. Localizing the key points such as eye corners, eye centers, nose center, jawline, etc gives the vital information needed for analysis of face status like expressions, health conditions, etc. The paper addresses a deep learning-based facial landmarks localization approach. MobileNet V3 is used to predict the facial landmarks on human faces which are mapped on the detected face in real-time. The model is evaluated with the wing and adaptive wing loss functions. The detector is examined with various head poses and occlusion conditions.

KW - Adaptive wing loss

KW - Facial landmarks

KW - Facial landmarks localization

KW - MobileNet

KW - Wing loss

UR - https://www.scopus.com/pages/publications/85098995270

U2 - 10.1109/ICTC49870.2020.9289429

DO - 10.1109/ICTC49870.2020.9289429

M3 - Conference contribution

AN - SCOPUS:85098995270

T3 - International Conference on ICT Convergence

SP - 584

EP - 587

BT - ICTC 2020 - 11th International Conference on ICT Convergence

PB - IEEE Computer Society

T2 - 11th International Conference on Information and Communication Technology Convergence, ICTC 2020

Y2 - 21 October 2020 through 23 October 2020

ER -

Deep Learning-Based Facial Landmarks Localization with Loss Comparison

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this