Introspective Gan for Meshface Recognition

Wenting Chen; Linlin Shen; Zhihui Lai

doi:10.1109/ICIP.2019.8803594

Introspective Gan for Meshface Recognition

Wenting Chen, Linlin Shen, Zhihui Lai

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

2 Citations (Scopus)

Abstract

Majority of face recognition systems can only retrieve protected ID photos from the government agency in China. These facial images covered with mesh-like curves are termed meshface. Meshface could significantly affect the performance of face recognition systems. Although some GAN based methods are proposed to address this issue by translating meshface images to clean face images, their capacities are limited. In this paper, we introduce the introspective modules to encourage the generator to reconstruct face images and accelerate the learning process of the discriminator. Both a private meshface dataset and the public LFW dataset are used for experiments. The quantitative evaluation on both datasets proves that the introspective GAN can recover face image with better quality. Additionally, face recognition performance is also significantly improved.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Publisher	IEEE Computer Society
Pages	3472-3476
Number of pages	5
ISBN (Electronic)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8803594
Publication status	Published - Sept 2019
Externally published	Yes
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China Duration: 22 Sept 2019 → 25 Sept 2019

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2019-September
ISSN (Print)	1522-4880

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country/Territory	Taiwan, Province of China
City	Taipei
Period	22/09/19 → 25/09/19

Keywords

GAN
Meshface recognition
image translation
introspective modules
mesh-like curves removal

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2019.8803594

Cite this

@inproceedings{a9c0f7e5ecc64141a84064b7106d6772,

title = "Introspective Gan for Meshface Recognition",

abstract = "Majority of face recognition systems can only retrieve protected ID photos from the government agency in China. These facial images covered with mesh-like curves are termed meshface. Meshface could significantly affect the performance of face recognition systems. Although some GAN based methods are proposed to address this issue by translating meshface images to clean face images, their capacities are limited. In this paper, we introduce the introspective modules to encourage the generator to reconstruct face images and accelerate the learning process of the discriminator. Both a private meshface dataset and the public LFW dataset are used for experiments. The quantitative evaluation on both datasets proves that the introspective GAN can recover face image with better quality. Additionally, face recognition performance is also significantly improved.",

keywords = "GAN, Meshface recognition, image translation, introspective modules, mesh-like curves removal",

author = "Wenting Chen and Linlin Shen and Zhihui Lai",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICIP.2019.8803594",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3472--3476",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

address = "United States",

}

Chen, W, Shen, L & Lai, Z 2019, Introspective Gan for Meshface Recognition. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8803594, Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, IEEE Computer Society, pp. 3472-3476, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, Province of China, 22/09/19. https://doi.org/10.1109/ICIP.2019.8803594

Introspective Gan for Meshface Recognition. / Chen, Wenting; Shen, Linlin; Lai, Zhihui.
2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. IEEE Computer Society, 2019. p. 3472-3476 8803594 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September).

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

TY - GEN

T1 - Introspective Gan for Meshface Recognition

AU - Chen, Wenting

AU - Shen, Linlin

AU - Lai, Zhihui

PY - 2019/9

Y1 - 2019/9

N2 - Majority of face recognition systems can only retrieve protected ID photos from the government agency in China. These facial images covered with mesh-like curves are termed meshface. Meshface could significantly affect the performance of face recognition systems. Although some GAN based methods are proposed to address this issue by translating meshface images to clean face images, their capacities are limited. In this paper, we introduce the introspective modules to encourage the generator to reconstruct face images and accelerate the learning process of the discriminator. Both a private meshface dataset and the public LFW dataset are used for experiments. The quantitative evaluation on both datasets proves that the introspective GAN can recover face image with better quality. Additionally, face recognition performance is also significantly improved.

AB - Majority of face recognition systems can only retrieve protected ID photos from the government agency in China. These facial images covered with mesh-like curves are termed meshface. Meshface could significantly affect the performance of face recognition systems. Although some GAN based methods are proposed to address this issue by translating meshface images to clean face images, their capacities are limited. In this paper, we introduce the introspective modules to encourage the generator to reconstruct face images and accelerate the learning process of the discriminator. Both a private meshface dataset and the public LFW dataset are used for experiments. The quantitative evaluation on both datasets proves that the introspective GAN can recover face image with better quality. Additionally, face recognition performance is also significantly improved.

KW - GAN

KW - Meshface recognition

KW - image translation

KW - introspective modules

KW - mesh-like curves removal

UR - http://www.scopus.com/inward/record.url?scp=85076814768&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2019.8803594

DO - 10.1109/ICIP.2019.8803594

M3 - Conference contribution

AN - SCOPUS:85076814768

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3472

EP - 3476

BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings

PB - IEEE Computer Society

T2 - 26th IEEE International Conference on Image Processing, ICIP 2019

Y2 - 22 September 2019 through 25 September 2019

ER -

Introspective Gan for Meshface Recognition

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this