Face Detection in Distorted Images Based on Image Restoration and Meta-learning

Xinru Liu, Mingtao Pei*, Wei Liang, Zhengang Nie

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Face detection in distorted images is a challenging task, and a natural idea is to conduct image restoration before face detection. Most of current image restoration techniques focus on improving the perceptual quality of the output image for single type of distortion, without taking the subsequent high-level detection task and unknown distortion into account. In this paper, we propose a restoration-based face detector in which the images are restored based on the detection loss instead of the perceptual quality loss, leading to better performance on subsequent detection task. Furthermore, we employ meta-learning to initialize the model with more appropriate parameters, thus our detector can adapt quickly to unseen distortions only using few examples with the corresponding distortion. Experiments on public datasets show that our proposed method could improve the performance of face detection in distorted images, and have a better generalization ability when applied to images with unseen distortions.

源语言英语
主期刊名Image and Graphics Technologies and Applications - 17th Chinese Conference, IGTA 2022, Revised Selected Papers
编辑Yongtian Wang, Huimin Ma, Yuxin Peng, Yue Liu, Ran He
出版商Springer Science and Business Media Deutschland GmbH
171-180
页数10
ISBN(印刷版)9789811950957
DOI
出版状态已出版 - 2022
活动17th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2022 - Virtual, Online
期限: 23 4月 202224 4月 2022

出版系列

姓名Communications in Computer and Information Science
1611 CCIS
ISSN(印刷版)1865-0929
ISSN(电子版)1865-0937

会议

会议17th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2022
Virtual, Online
时期23/04/2224/04/22

指纹

探究 'Face Detection in Distorted Images Based on Image Restoration and Meta-learning' 的科研主题。它们共同构成独一无二的指纹。

引用此