形状空间下的3D面貌相似性比较  

3D facial similarity comparison in shape space

作　　者：赵俊莉[1,2] 武仲科[2] 刘翠婷[2] 段福庆[2] 周明全[2] 曹嘉谊 

机构地区：[1]青岛大学软件技术学院,山东青岛266071 [2]北京师范大学信息科学与技术学院虚拟现实应用教育部工程研究中心,北京100875 [3]天津中医药大学中药学院,天津300193

出　　处：《光学精密工程》2015年第4期1138-1145,共8页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.61170170;No.61272363);国家科技支撑计划资助项目(No.2012BAH33F04);教育部新世纪优秀人才支持计划资助项目(No.NCET-13-0051);中央高校基本科研业务费专项资金资助项目(No.2013YB13;No.2013YB70);北京市自然科学基金资助项目(No.4152028)

摘　　要：开展了利用计算机自动比较两个3D面貌相似程度的研究。提出了一种在形状空间下基于测地线的3D面貌相似性比较的方法。该方法使用测地线近似表示3D面貌模型,然后将其变换到形状空间下,以对应测地线的平均测地距离作为两个3D面貌的相似性比较的依据。在公开的GAVADB三维面貌库上对14个人的28个3D面貌模型进行了实验,识别率达到92.86%以上,说明本方法可以将同一个人的不同模型与不同人的模型区分开。另外,使用提出的方法对不同人的3D面貌模型进行了相似性比较实验,结果表明使用本方法得出的相似程度的判断与人的主观判断相一致,说明本方法能够较好地反应3D面貌的相似程度。This paper focuses on the 3D facial similarity comparison by using a computer automatically.A new 3Dfacial similarity comparison method based on a geodesics in a shape space was proposed.In this method,3Dfacial surface was approximately represented by a set of geodesics and the corresponding geodesics between two facial models were compared by a elastic metric in the shape space,in which the similarity between two faces could be measured by the average geodesic distance of all corresponding geodesics.3Dfacial similarity experiments were perfomed on 28 facial models of 14 persons in Gavadb database and the recognition rate is above 92.86%,which indicates that this method recognizes the facial models of the same person from different person＇s facial models.In addition,3Dfacial similarity experiments on different person＇s facial models were implemented.The experimental results show that the similarity values computed by proposed method consist with that of people＇s subjective judgment.These results reflect that the proposed method can measure the similarity of 3Dfaces well.

关 键 词：计算机图形学 计算机视觉 3D面貌相似性 测地线 形状空间 平方根速度函数(SRVF) 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]