With computer vision reaching an inflection point in the past decade, face recognition technology has become pervasive in policing, intelligence gathering, and consumer applications. Recently, face recognition technology has been deployed on bodyworn cameras to keep officers safe, enabling situational awareness and providing evidence for trial. However, limited academic research has been conducted on this topic using traditional techniques on datasets with small sample size. This paper aims to bridge the gap in the state-of-the-art face recognition using bodyworn cameras (BWC). To this aim, the contribution of this work is two-fold: (1) collection of a dataset called BWCFace consisting of a total of 178K facial images of 132 subjects captured using the body-worn camera in in-door and daylight conditions, and (2) open-set evaluation of the latest deep-learning-based Convolutional Neural Network (CNN) architectures combined with five different loss functions for face identification, on the collected dataset. Experimental results on our BWCFace dataset suggest a maximum of 33.89% Rank-1 accuracy obtained when facial features are extracted using SENet-50 trained on a large scale VGGFace2 facial image dataset. However, performance improved up to a maximum of 99.00% Rank-1 accuracy when pretrained CNN models are fine-tuned on a subset of identities in our BWCFace dataset. Equivalent performances were obtained across body-worn camera sensor models used in existing face datasets. The collected BWCFace dataset and the pretrained/ fine-tuned algorithms are publicly available to promote further research and development in this area. A downloadable link of this dataset and the algorithms is available by contacting the authors.

中文翻译：

---

BWCFace：使用随身相机的开放式人脸识别

随着计算机视觉在过去十年达到一个拐点，人脸识别技术在警务、情报收集和消费者应用中变得普遍。最近，人脸识别技术已被部署在随身摄像机上，以确保警官的安全，实现态势感知并为审判提供证据。然而，使用传统技术对小样本数据集进行的学术研究有限。本文旨在弥补使用随身相机（BWC）的最先进人脸识别的差距。为此，这项工作的贡献有两个方面：(1) 收集了一个名为 BWCFace 的数据集，该数据集由在室内和日光条件下使用随身相机拍​​摄的 132 个对象的 178K 面部图像组成，(2) 在收集的数据集上对最新的基于深度学习的卷积神经网络 (CNN) 架构与五种不同的面部识别损失函数相结合的开放集评估。在我们的 BWCFace 数据集上的实验结果表明，当使用在大规模 VGGFace2 面部图像数据集上训练的 SENet-50 提取面部特征时，最高可以获得 33.89% Rank-1 的准确率。然而，当预训练的 CNN 模型在我们的 BWCFace 数据集中的身份子集上进行微调时，性能提高到最高 99.00% Rank-1 准确度。在现有面部数据集中使用的穿戴式相机传感器模型中获得了等效的性能。收集到的 BWCFace 数据集和预训练/微调算法已公开可用，以促进该领域的进一步研究和开发。