Face Detection and Verification Using Lensless Cameras
Face Detection and Verification Using Lensless Cameras
复制标题
DOI：
10.1109/tci.2018.2889933
复制
发表时间：
2019-06
影响因子：
5.4
通讯作者：
Jasper Tan;Li Niu;Jesse K. Adams;Vivek Boominathan;Jacob T. Robinson;Richard Baraniuk;A. Veeraraghavan
中科院分区：
文献类型：
--
作者：
Jasper Tan;Li Niu;Jesse K. Adams;Vivek Boominathan;Jacob T. Robinson;Richard Baraniuk;A. Veeraraghavan
基于摄像头的人脸检测和验证已经发展到可以集成到无数应用中的程度，从家用电器到物联网设备再到无人机。其中许多应用对相机封装的外形、重量和成本施加了严格的限制，而当前一代基于镜头的成像器无法满足这些限制。无镜头成像系统提供了一种越来越有前途的替代方案，它从根本上改变了相机系统的外形尺寸并降低了重量和成本。然而，无镜头成像仪目前无法提供与基于镜头的成像仪相同的图像分辨率和清晰度。本文详细介绍了对无透镜成像系统在人脸检测和验证方面的潜力和功效的首次评估。我们建议使用现有的深度学习技术进行人脸检测和验证，以解决当今无镜头相机固有的分辨率、噪声和伪影问题。我们证明，可以根据无镜头相机获取的图像高精度地执行人脸检测和验证，这为将其集成到新应用中铺平了道路。我们研究的一个关键组成部分是使用 FlatCam 在不同操作条件下拍摄的 88 名受试者的 24 112 张无镜头相机图像组成的数据集。
Camera-based face detection and verification have advanced to the point where they are ready to be integrated into myriad applications, from household appliances to Internet of Things devices to drones. Many of these applications impose stringent constraints on the form-factor, weight, and cost of the camera package that cannot be met by current-generation lens-based imagers. Lensless imaging systems provide an increasingly promising alternative that radically changes the form-factor and reduces the weight and cost of a camera system. However, lensless imagers currently cannot offer the same image resolution and clarity of their lens-based counterparts. This paper details a first-of-its-kind evaluation of the potential and efficacy of lensless imaging systems for face detection and verification. We propose the usage of existing deep learning techniques for face detection and verification that account for the resolution, noise, and artifacts inherent in today's lensless cameras. We demonstrate that both face detection and verification can be performed with high accuracy from the images acquired from lensless cameras, which paves the way to their integration into new applications. A key component of our study is a dataset of 24 112 lensless camera images captured using FlatCam of 88 subjects in a range of different operating conditions.