ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2021, Vol. 58 ›› Issue (12): 2760-2782.doi: 10.7544/issn1000-1239.2021.20200870

• 人工智能 • 上一篇    下一篇

基于深度学习的人脸属性识别方法综述

赖心瑜1,2,陈思1,2,严严3,王大寒1,2,朱顺痣1,2   

  1. 1(厦门理工学院计算机与信息工程学院 福建厦门 361024);2(福建省模式识别与图像理解重点实验室(厦门理工学院) 福建厦门 361024);3(厦门大学信息学院 福建厦门 361005) (laixinyu@stu.xmut.edu.cn)
  • 出版日期: 2021-12-01
  • 基金资助: 
    国家自然科学基金面上项目(62071404,61773325);福建省自然科学基金面上项目(2021J011185,2020J01001);福建省科技计划项目(2020H0023);厦门市青年创新基金项目(3502Z20206068)

Survey on Deep Learning Based Facial Attribute Recognition Methods

Lai Xinyu1,2, Chen Si1,2, Yan Yan3, Wang Dahan1,2, Zhu Shunzhi1,2   

  1. 1(School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, Fujian 361024);2(Fujian Key Laboratory of Pattern Recognition and Image Understanding(Xiamen University of Technology), Xiamen, Fujian 361024);3(School of Informatics, Xiamen University, Xiamen, Fujian 361005)
  • Online: 2021-12-01
  • Supported by: 
    This work was supported by the General Program of the National Natural Science Foundation of China (62071404, 61773325), the General Program of the Natural Science Foundation of Fujian Province (2021J011185, 2020J01001), the Science and Technology Planning Project of Fujian Province (2020H0023), and the Youth Innovation Foundation of Xiamen City (3502Z20206068).

摘要: 人脸属性识别是计算机视觉和模式识别领域的热门研究课题之一,对人脸图像的分析和理解具有重要的研究意义,同时在图像检索、人脸识别、微表情识别和推荐系统等诸多领域具有广泛的实际应用价值.随着深度学习的快速发展,目前国内外学者已提出许多基于深度学习的人脸属性识别(deep learning based facial attribute recognition, DFAR)方法.首先,阐述人脸属性识别方法的总体流程.接着,按照不同的模型构建方式,分别对基于部分的与基于整体的DFAR方法进行详细地概述与讨论.具体地,对基于部分的DFAR方法按是否采用规则区域定位进行分类,而对基于整体的DFAR方法则分别从基于单任务学习、基于多任务学习的角度进行区分,并对基于多任务学习的DFAR方法根据是否采用属性分组来进一步细分.然后介绍了常用的人脸属性识别数据集与评价指标,并对比与分析了新近提出的DFAR方法的性能.最后对DFAR方法的未来研究趋势进行展望.

关键词: 人脸属性识别, 深度学习, 多标记学习, 单任务学习, 多任务学习

Abstract: Facial attribute recognition is one of the most popular research topics in computer vision and pattern recognition, and has great research significance of analyzing and understanding facial images. At the same time, it has a wide range of practical application value in many fields such as image retrieval, face recognition, micro-expression recognition and recommendation system. With the rapid development of deep learning, a large number of deep learning based facial attribute recognition (termed DFAR) methods have been put forward by domestic and foreign scholars. First the overall process of the facial attribute recognition method is described. Then, according to the different mechanisms of model construction, the part-based and holistic DFAR methods are reviewed and discussed in detail, respectively. Specifically, the part-based DFAR methods are classified according to whether or not to adopt the regular area localization technique, while the holistic DFAR methods are distinguished from the perspectives of single-task learning and multi-task learning, where multi-task learning based DFAR methods are further subdivided according to whether the attribute grouping strategy is used. Next, several popular databases and evaluation metrics on facial attribute recognition are introduced, and the performance of the state-of-the-art DFAR methods is compared and analyzed. Finally, the future research directions of the DFAR methods are provided.

Key words: facial attribute recognition, deep learning, multi-label learning, single-task learning, multi-task learning

中图分类号: