期刊
NEURAL PROCESSING LETTERS
卷 39, 期 1, 页码 25-43出版社
SPRINGER
DOI: 10.1007/s11063-013-9288-7
关键词
Face recognition; Micro-expression recognition; Locality preserving projection; Discriminant information; Tensor subspace; Extreme learning machine
资金
- 973 Program [2011CB302201]
- National Natural Science Foundation of China [61075042, 61175023]
- China Postdoctoral Science Foundation [2012M520428]
In this paper, a novel recognition algorithm based on discriminant tensor subspace analysis (DTSA) and extreme learning machine (ELM) is introduced. DTSA treats a gray facial image as a second order tensor and adopts two-sided transformations to reduce dimensionality. One of the many advantages of DTSA is its ability to preserve the spatial structure information of the images. In order to deal with micro-expression video clips, we extend DTSA to a high-order tensor. Discriminative features are generated using DTSA to further enhance the classification performance of ELM classifier. Another notable contribution of the proposed method includes significant improvements in face and micro-expression recognition accuracy. The experimental results on the ORL, Yale, YaleB facial databases and CASME micro-expression database show the effectiveness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据