arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01745cs.CVcs.LG
收藏

一种真实的面具人脸生成方法在两种新的面具人脸识别数据集上的应用

A realistic approach to generate masked faces applied on two novel masked face recognition data sets

SecurifAI;University of Bucharest(布加勒斯特大学)

Tudor Mare, Georgian Duta, Mariana-Iuliana Georgescu, Adrian Sandru, Bogdan Alexe, Marius Popescu, Radu Tudor Ionescu

摘要:

COVID-19大流行提出了使人脸识别系统适应新现实的问题,人们可能会戴上外科口罩来遮住鼻子和嘴。传统数据集(例如,用于训练这些系统的CelebA、CASIA-WebFace)是在大流行之前发布的,因此,由于缺乏人们戴口罩的例子,它们现在似乎不适合。我们提出了一种方法来增强数据集包含的脸没有面具,通过创建合成面具,并将它们覆盖在原始图像中的脸。我们的方法依赖于SparkAR Studio,这是一个由Facebook开发的开发人员程序,用于创建Instagram的面部过滤器。在我们的方法中,我们使用9种不同颜色,形状和面料的面具。我们使用我们的方法为CASIA-WebFace数据集生成了445,446(90%)个面具样本,为CelebA数据集生成了196,254(96.8%)个面具样本,并在www.example.com上发布了面具图像。我们表明,我们的方法产生了显着更现实的训练样本的面具覆盖在脸上,要求志愿者进行定性比较,它与其他方法或数据集设计用于相同的任务。我们还通过评估在我们增强的数据集上训练的最先进的人脸识别系统(FaceNet,VGG-face,ArcFace)来证明我们的方法的有用性,并表明它们优于在原始数据集(包含没有面具的脸)或竞争数据集(包含相关方法生成的面具)上训练的等效系统,当测试基准包含面具时。

英文摘要:

The COVID-19 pandemic raises the problem of adapting face recognition systems to the new reality, where people may wear surgical masks to cover their noses and mouths. Traditional data sets (e.g., CelebA, CASIA-WebFace) used for training these systems were released before the pandemic, so they now seem unsuited due to the lack of examples of people wearing masks. We propose a method for enhancing data sets containing faces without masks by creating synthetic masks and overlaying them on faces in the original images. Our method relies on SparkAR Studio, a developer program made by Facebook that is used to create Instagram face filters. In our approach, we use 9 masks of different colors, shapes and fabrics. We employ our method to generate a number of 445,446 (90%) samples of masks for the CASIA-WebFace data set and 196,254 (96.8%) masks for the CelebA data set, releasing the mask images at https://github.com/securifai/masked_faces. We show that our method produces significantly more realistic training examples of masks overlaid on faces by asking volunteers to qualitatively compare it to other methods or data sets designed for the same task. We also demonstrate the usefulness of our method by evaluating state-of-the-art face recognition systems (FaceNet, VGG-face, ArcFace) trained on our enhanced data sets and showing that they outperform equivalent systems trained on original data sets (containing faces without masks) or competing data sets (containing masks generated by related methods), when the test benchmarks contain masked faces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑