有遮挡人脸识别进展综述

Review of progress of face recognition with occlusion

人脸识别技术水平不断提升,在身份认证、人机交互等应用上得到了较为理想的识别率,市场规模不断增长。然而真实场景下的遮挡问题并没有被彻底解决,如何抑制或消除遮挡对人脸关键性特征的负面影响是当前人脸识别领域的热点之一。针对遮挡导致的人脸结构信息缺失问题,对有遮挡人脸识别数据集和有遮挡人脸识别方法进行综述,首先介绍分析了一些重要的新型有遮挡人脸识别数据集;其次,归纳分析了用于解决遮挡问题的传统方法和深度学习方法,重点介绍了基于深度学习的特征鲁棒性提取方法和遮挡部位信息恢复方法;最后,总结分析了相关方法的优缺点,指出有遮挡人脸识别研究存在的问题和挑战,对未来研究方向进行了展望。

The level of face recognition technology continues to improve,and has achieved an ideal recognition rate in identity authentication,human-computer interaction and other industrial applications,and the market scale keeps growing.However,the occlusion problem in real scenes has not been completely solved.How to restrain or eliminate the negative impact of occlusion on key facial feature,is one of the hot spots in the field of face recognition.Aiming at the problem of lack of face structure information caused by occlusion,this paper reviewed the occluded face recognition datasets and the occluded face recognition methods.Firstly,it introduced and analyzed some important new occluded face recognition datasets.Secondly,it summarized the traditional learning methods and deep learning based methods to solve occlusion problems,and emphasized the deep lear-ning based robustness feature extraction and occluded facial information recovery.Finally,this paper summarized and analyzed the advantages and disadvantages of relevant methods,pointed out the problems and challenges of occluded face recognition,and prospected the future research directions.