Regularized latent least square regression for cross pose face recognition | |
Xinyuan Cai; Chunheng Wang; Baihua Xiao; Xue Chen; Ji Zhou; Wang.Chunheng | |
2013 | |
会议名称 | Twenty-Third international joint conference on Artificial Intelligence(IJCAI '13) |
会议录名称 | International Joint Conference on Artificial Intelligence (IJCAI ) |
页码 | 1247-1253 |
会议日期 | 2013 |
会议地点 | Beijing,China |
摘要 | Pose variation is one of the challenging factors for face recognition. In this paper, we propose a novel cross-pose face recognition method named as Regularized Latent Least Square Regression (RLLSR). The basic assumption is that the images captured under different poses of one person can be viewed as pose-specific transforms of a single ideal object. We treat the observed images as regressor, the ideal object as response, and then formulate this assumption in the least square regression framework, so as to learn the multiple pose-specific transforms. Specifically, we incorporate some prior knowledge as two regularization terms into the least square approach: 1) the smoothness regularization, as the transforms for nearby poses should not differ too much; 2) the local consistency constraint, as the distribution of the latent ideal objects should preserve the geometric structure of the observed image space. We develop an alternating algorithm to simultaneously solve for the ideal objects of the training individuals and a set of pose-specific transforms. The experimental results on the Multi-PIE dataset demonstrate the effectiveness of the proposed method and superiority over the previous methods. |
关键词 | Face Recognition |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/5151 |
专题 | 复杂系统管理与控制国家重点实验室_影像分析与机器视觉 |
通讯作者 | Wang.Chunheng |
推荐引用方式 GB/T 7714 | Xinyuan Cai,Chunheng Wang,Baihua Xiao,et al. Regularized latent least square regression for cross pose face recognition[C],2013:1247-1253. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
201018014628026_002.(653KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论