文献类型：期刊文献

中文题名：Face recognition using SIFT features under 3D meshes

英文题名：Face recognition using SIFT features under 3D meshes

作者：Zhang Cheng[1];Gu Yu-zhang[1];Hu Ke-li[2];Wang Ying-guan[1]

机构：[1]Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Key Lab Wireless Sensor Network & Commun, Shanghai 201800, Peoples R China;[2]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China

年份：2015

卷号：22

期号：5

起止页码：1817

中文期刊名：中南大学学报：英文版

外文期刊名：JOURNAL OF CENTRAL SOUTH UNIVERSITY

收录：SCI-EXPANDED(收录号：WOS:000354988900026)、CSTPCD、、EI(收录号：20152200881848)、CSCD2015_2016、Scopus(收录号：2-s2.0-84930008100)、WOS、CSCD

基金：Foundation item: Project(XDA06020300) supported by the "Strategic Priority Research Program" of the Chinese Academy of Sciences; Project(12511501700) supported by the Research on the Key Technology of Internet of Things for Urban Community Safety Based on Video Sensor networks

语种：英文

中文关键词：3D;face;recognition;scale-invariant;feature;transform(SIFT);expression;occlusion;large;pose;changes;3D;meshes;

外文关键词：3D face recognition; scale-invariant feature transform (SIFT); expression; occlusion; large pose changes; 3D meshes

中文摘要：Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform(SIFT) features on 3D meshes. After preprocessing, shape index extrema on the 3D facial surface are selected as keypoints in the difference scale space and the unstable keypoints are removed after two screening steps. Then, a local coordinate system for each keypoint is established by principal component analysis(PCA).Next, two local geometric features are extracted around each keypoint through the local coordinate system. Additionally, the features are augmented by the symmetrization according to the approximate left-right symmetry in human face. The proposed method is evaluated on the Bosphorus, BU-3DFE, and Gavab databases, respectively. Good results are achieved on these three datasets. As a result, the proposed method proves robust to facial expression variations, partial external occlusions and large pose changes.

外文摘要：Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform (SIFT) features on 3D meshes. After preprocessing, shape index extrema on the 3D facial surface are selected as keypoints in the difference scale space and the unstable keypoints are removed after two screening steps. Then, a local coordinate system for each keypoint is established by principal component analysis (PCA). Next, two local geometric features are extracted around each keypoint through the local coordinate system. Additionally, the features are augmented by the symmetrization according to the approximate left-right symmetry in human face. The proposed method is evaluated on the Bosphorus, BU-3DFE, and Gavab databases, respectively. Good results are achieved on these three datasets. As a result, the proposed method proves robust to facial expression variations, partial external occlusions and large pose changes.