TechRxiv
TechRxiv-submission-DOI12333176.pdf (10.47 MB)

Complete Face Recovering: An Approach towards Recognizing a Person by a Single Partial Face Image without the Target Photo in Gallery

Download (10.47 MB)
preprint
posted on 21.05.2020, 07:38 by Yiu-ming Cheung, Mengke Li
Complete face recovering (CFR) is to recover the complete face image of a given partial face image of a target person whose photo may not be included in the gallery set. The CFR has several attractive potential applications but is challenging. As far as we know, the CFR problem has yet to be explored in the literature. This paper therefore proposes an identity-preserved CFR approach (IP-CFR) to addressing the CFR. First, a denoising auto-encoder based network is applied to acquire the discriminative feature. Then, we propose an identity-preserved loss function to keep the personal identity information. Furthermore, the acquired features are fed into a new variant of the generative adversarial network (GAN) to restore the complete face image. In addition, a two-pathway discriminator is leveraged to enhance the quality of the recovered image. Experimental results on the benchmark datasets show the promising result of the proposed approach.

History

Email Address of Submitting Author

ymc@comp.hkbu.edu.hk

ORCID of Submitting Author

0000-0001-7629-4648

Submitting Author's Institution

Hong Kong Baptist University

Submitting Author's Country

Hong Kong

Licence

Exports

Licence

Exports