Face image classification by pooling raw features
详细信息 查看全文
- 作者：Fumin Shena ; fumin.shen@gmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Chunhua Shenb ; chunhua.shen@adelaide.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Xiang Zhoua ; Johnfly2000@gmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Yang Yanga ; dlyyang@gmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Heng Tao Shena ; c ; shenhengtao@hotmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Face recognition ; Image classification ; Feature pooling
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：June 2016
- 年：2016
- 卷：54
- 期：Complete
- 页码：94-103
- 全文大小：1136 K
文摘
- •
We propose the first face feature extraction method by directly pooling raw patches.
- •
The method can capture strong structural information of individual faces.
- •
The method achieves state-of-the-art results on several face recognition datasets.
- •
Multi-level spatial pooling and dense extraction of local patches play critical roles.