TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition
TV-GAN: Generative Adversarial Network Based Thermal to Visible Face Recognition
复制标题
TV-GAN：基于生成对抗网络的热可见人脸识别
DOI：
10.1109/icb2018.2018.00035
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
B. Lovell
中科院分区：
文献类型：
--
作者：
Teng Zhang;A. Wiliem;Siqi Yang;B. Lovell
这项工作解决了使用热像仪传感器捕获的图像上的人脸识别任务，热像仪传感器可以在非光环境中工作。虽然它可以极大地增加当前安全监控系统的范围和好处，但与可见光领域(VLD)的人脸识别任务相比，使用热像执行此类任务是一个具有挑战性的问题。这在一定程度上是因为与VLD数据相比，收集的热成像数据量要小得多。不幸的是，将现有的使用VLD数据训练的非常强的人脸识别模型直接应用到热图像数据中不会产生令人满意的性能。这是由于热像和VLD像之间存在磁区间隙所致。为此，我们提出了一种热到可见的生成性对抗网络(TV-GAN)，它能够将热人脸图像转换成相应的VLD图像，同时保持足够的身份信息，足以让现有的VLD人脸识别模型进行识别。图1中给出了一些例子。与以前的方法不同，我们提出的TV-GAN使用显式闭集人脸识别损失来规则化鉴别器网络训练。然后，这些信息将以梯度损耗的形式传输到发电机网络。在实验中，我们表明，通过对鉴别器网络使用这种额外的显式正则化，TV-GAN在翻译TV-GAN之前没有看到的人的热像时能够保留更多的身份信息。
This work tackles the face recognition task on images captured using thermal camera sensors which can operate in the non-light environment. While it can greatly increase the scope and benefits of the current security surveillance systems, performing such a task using thermal images is a challenging problem compared to face recognition task in the Visible Light Domain (VLD). This is partly due to the significantly smaller amount of thermal imagery data collected compared to the VLD data. Unfortunately, direct application of the existing very strong face recognition models trained using VLD data into the thermal imagery data will not produce a satisfactory performance. This is due to the existence of the domain gap between the thermal and VLD images. To this end, we propose a Thermal-to-Visible Generative Adversarial Network (TV-GAN) that is able to transform thermal face images into their corresponding VLD images whilst maintaining identity information which is sufficient enough for the existing VLD face recognition models to perform recognition. Some examples are presented in Figure 1. Unlike the previous methods, our proposed TV-GAN uses an explicit closed-set face recognition loss to regularize the discriminator network training. This information will then be conveyed into the generator network in the form of gradient loss. In the experiment, we show that by using this additional explicit regularization for the discriminator network, the TV-GAN is able to preserve more identity information when translating a thermal image of a person which is not seen before by the TV-GAN.