Combining Local and Global Features for Face Recognition

• Item type: SIG Technical Reports(1)
• 公開日: 2007-09-03
• タイトル: Combining Local and Global Features for Face Recognition
• タイトル / 言語: en
• タイトル: Combining Local and Global Features for Face Recognition
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Institute of Computing Technology Chinese Academy of Sciences
• 著者所属: Institute of Computing Technology Chinese Academy of Sciences
• 著者所属: School of Computer Science and Technology Harbin Institute of Technology
• 著者所属: School of Computer Science and Technology Harbin In
• 著者所属(英): en
• 著者所属(英): Institute of Computing Technology, Chinese Academy of Sciences
• 著者所属(英): en
• 著者所属(英): Institute of Computing Technology, Chinese Academy of Sciences
• 著者所属(英): en
• 著者所属(英): School of Computer Science and Technology, Harbin Institute of Technology
• 著者所属(英): en
• 著者所属(英): School of Computer Science and Technology, Harbin Institute of Technology
• 著者所属(英): en
• 著者所属(英): School of Computer Science and Technology, Harbin Institute of Technology
• 著者所属(英): en
• 著者所属(英): Institute of Computing Technology, Chinese Academy of Sciences / Institute of Computing Technology, Chinese Academy of Sciences
• 著者名: Xilin, Chen; Shiguang, Shan; Yu, Su; Wenchao, Zhang; Baochang, Zhang; Wen, Gao
• 著者名(英): Xilin, Chen; Shiguang, Shan; Yu, Su; Wenchao, Zhang; Baochang, Zhang; Wen, Gao
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In the literature of psychophysics and neurophysiology many studies have shown that both global and local features are crucial for face recognition. In this paper we summarize our work on face recognition by combining both local and global discriminative features. In our work Fourier transform is exploited to extract global features from the whole face image domain. For local feature Gabor wavelets and its combination with Local Binary Patterns (LBP) are explored which are both conducted on some spatially partitioned image patches. These features are then fed into different classifiers based on Fisher Discriminant Analysis respectively and these classifiers are combined together to make the final decision. The proposed methods are evaluated by using Face Recognition Grand Challenge (FRGC) experimental protocols and database the largest data sets available. Experimental results on FRGC version 2.0 dataset show that our methods have much higher verification rates than the baseline of FRGC and the best known results under various situations such as illumination changes expression changes and time elapses.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In the literature of psychophysics and neurophysiology, many studies have shown that both global and local features are crucial for face recognition. In this paper, we summarize our work on face recognition by combining both local and global discriminative features. In our work, Fourier transform is exploited to extract global features from the whole face image domain. For local feature, Gabor wavelets and its combination with Local Binary Patterns (LBP) are explored, which are both conducted on some spatially partitioned image patches. These features are then fed into different classifiers based on Fisher Discriminant Analysis respectively, and these classifiers are combined together to make the final decision. The proposed methods are evaluated by using Face Recognition Grand Challenge (FRGC) experimental protocols and database, the largest data sets available. Experimental results on FRGC version 2.0 dataset show that our methods have much higher verification rates than the baseline of FRGC and the best known results under various situations such as illumination changes, expression changes, and time elapses.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11131797
• 書誌情報: 情報処理学会研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2007, 号 87(2007-CVIM-160), p. 111-118, 発行日 2007-09-03
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会