基于区域分割的表情鲁棒三维人脸识别方法  

Region-based expression invariant 3D face recognition

作　　者：桑高丽 郑增国 闫超 Sang Gaoli;Zheng Zengguo;Yan Chao(School of Mathematics&Information Engineering,Jiaxing University,Jiaxing Zhejiang 314001,China;Computer Network Center,Shangrao Normal University,Shangrao Jiangxi 334000,China;Ideals Technology(Chengdu)Co.,Ltd.,Chengdu 610000,China)

机构地区：[1]嘉兴学院数理与信息工程学院,浙江嘉兴314001 [2]上饶师范学院计算机网络中心,江西上饶334000 [3]成都理想境界科技有限公司,成都610000

出　　处：《计算机应用研究》2020年第3期914-918,共5页Application Research of Computers

基　　金：浙江省自然科学基金青年基金资助项目(LQ18F020007)。

摘　　要：为了克服表情变化致使三维人脸识别性能不佳的问题,提出基于鼻尖点区域分割的表情鲁棒三维人脸识别方法。首先,根据表情对人脸影响具有区域性的特点,提出仅依赖鼻尖点的表情不变区域(刚性区域)和表情易变(非刚性区域)划分方法;然后针对表情不变区域和表情易变区域使用不同的特征描述方式并计算匹配相似度;最后将表情不变区域和表情易变的相似度进行加权融合实现最终身份识别。提出方法分别在FRGC v2.0和自建WiseFace表情人脸数据库上达到98.52%和99.01%的rank 1识别率,证明该方法对表情变化具有较强的鲁棒性。In order to overcome the problems caused by expressions in 3D face recognition,this paper proposed a new method based on nose tip segmentation.First,in order to weaken the effects of facial expression,it proposed a new method that only needed nose tip of dividing faces into rigid and non-rigid regions.Then,considering the discrimination ability of rigid and non-rigid regions,this paper employed different 3D face features of the rigid and non-rigid 3D face regions.At last,the method fused the rigid and non-rigid face features to address the recognition task.Experimental results on the FRGC v2.0 and self-built WiseFace databases show that the proposed method is robust to expression variations.The rank-one face recognitions rates on the two databases are 98.52%and 99.01%separately.

关 键 词：表情变化 三维人脸识别 区域分割 刚性/非刚性区域 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]