Automatic Face Image Quality Prediction
Lacey Best-Rowden, and Anil K. Jain L. Best-Rowden and A. K. Jain are with the Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, 48824. E-mail: {bestrow1,
Abstract
Face image quality can be defined as a measure of the utility of a face image to automatic face recognition. In this work, we propose (and compare) two methods for automatic face image quality based on target face quality values from (i) human assessments of face image quality (matcher-independent), and (ii) quality values computed from similarity scores (matcher-dependent). A support vector regression model trained on face features extracted using a deep convolutional neural network (ConvNet) is used to predict the quality of a face image. The proposed methods are evaluated on two unconstrained face image databases, LFW and IJB-A, which both contain facial variations with multiple quality factors. Evaluation of the proposed automatic face image quality measures shows we are able to reduce the FNMR at 1% FMR by at least 13% for two face matchers (a COTS matcher and a ConvNet matcher) by using the proposed face quality to select subsets of face images and video frames for matching templates (i.e., multiple faces per subject) in the IJB-A protocol. To our knowledge, this is the first work to utilize human assessments of face image quality in designing a predictor of unconstrained fac
中文速览
人脸图像质量直接决定自动人脸识别系统的准确率，但如何客观衡量"哪张脸更好识别"一直缺乏系统性研究。这项工作同时提出并对比了两种自动人脸图像质量预测方法：一种基于众包收集的人类主观质量评分（与识别算法无关），另一种基于人脸匹配器的相似度分数推导出的质量值（与识别算法相关），再用深度卷积神经网络提取图像特征、结合支持向量回归训练质量预测模型。实验在LFW和IJB-A两个无约束人脸数据库上验证，结果表明：将预测到的质量分数用于筛选模板中的人脸图像，能使两个主流匹配器（商业系统和深度学习系统）在1% FMR下的错误拒绝率（FNMR）至少降低13%。这项研究首次将人类对无约束人脸图像的质量感知系统性地引入质量预测模型，并证明人类判断在跨数据库场景下对提升自动识别性能同样有效。
原文 arXiv:1706.09887;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1706.09887v1