Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (6): 1685-1689.DOI: 10.11772/j.issn.1001-9081.2018112301

• Artificial intelligence • Previous Articles     Next Articles

Expression-insensitive three-dimensional face recognition algorithm based on multi-region fusion

SANG Gaoli1, YAN Chao2, ZHU Rong1   

  1. 1. College of Mathematics and Information Engineering, Jiaxing University, Jiaxing Zhejiang 314001, China;
    2. College of Computer Science, Sichuan University, Chengdu Sichuan 610064, China
  • Received:2018-11-17 Revised:2018-12-24 Online:2019-06-10 Published:2019-06-17
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61703183), the Natural Science Foundation of Zhejiang Province (LY15F020039, LQ18F020007, LQ18F020006).

基于多区域融合的表情鲁棒三维人脸识别算法

桑高丽1, 闫超2, 朱蓉1   

  1. 1. 嘉兴学院 数理与信息工程学院, 浙江 嘉兴 314001;
    2. 四川大学 计算机学院, 成都 610064
  • 通讯作者: 桑高丽
  • 作者简介:桑高丽(1986-),女,河南鹿邑人,讲师,博士,主要研究方向:模式识别、人工智能;闫超(1985-),男,山东菏泽人,高级工程师,硕士,主要研究方向:人工智能;朱蓉(1973-),女,浙江嘉兴人,教授,博士,主要研究方向:数据挖掘、智能计算。
  • 基金资助:
    国家自然科学基金资助项目(61703183);浙江省自然科学基金资助项目(LY15F020039,LQ18F020007,LQ18F020006)。

Abstract: In order to realize the robustness of three-Dimensional (3D) face recognition algorithm to expression variations, a multi-region template fusion 3D face recognition algorithm based on semantic alignment was proposed. Firstly, in order to guarantee the semantic alignment of 3D faces, all the 3D face models were densely aligned with a pre-defined standard reference 3D face model. Then, considering the expressions were regional, to be robust to region division, a multi-region template based similarity prediction method was proposed. Finally, all the prediction results of multiple classifiers were fused by majority voting method. The experimental results show that, the proposed algorithm can achieve the rank-1 face recognition rate of 98.69% on FRGC (the Face Recognition Grand Challenge) v2.0 expression 3D face database and rank-1 face recognition rate of 84.36% on Bosphorus database with occlusion change.

Key words: expression variation, three-Dimensional (3D) face recognition, multi-region template, majority voting

摘要: 为了实现三维人脸识别算法对表情变化的鲁棒性,提出一种基于语义对齐的多区域模板融合三维人脸识别算法。首先,为了实现三维人脸在语义上的对齐,将所有三维人脸模型与预定义标准参考模型做稠密对齐。然后,根据人脸表情具有区域性的特点,为了不受限于区域划分的精准度,提出基于多区域模板的相似度预测方法。最后,采用多数投票法将多个分类器的预测结果融合得到最终识别结果。实验结果表明,在FRGC v2.0表情三维人脸数据库上所提算法可以达到98.69%的rank-1识别率,在含有遮挡变化的Bosphorus数据库上该算法达到84.36%的rank-1识别率。

关键词: 表情变化, 三维人脸识别, 多区域模板, 多数投票

CLC Number: