发明授权
- 专利标题: Face recognition using discriminatively trained orthogonal tensor projections
- 专利标题(中): 使用区分训练正交张量投影的人脸识别
-
申请号: US11763909申请日: 2007-06-15
-
公开(公告)号: US07936906B2公开(公告)日: 2011-05-03
- 发明人: Gang Hua , Paul A Viola , Steven M. Drucker , Michael Revow
- 申请人: Gang Hua , Paul A Viola , Steven M. Drucker , Michael Revow
- 申请人地址: US WA Redmond
- 专利权人: Microsoft Corporation
- 当前专利权人: Microsoft Corporation
- 当前专利权人地址: US WA Redmond
- 代理机构: Lee & Hayes, PLLC
- 主分类号: G06K9/00
- IPC分类号: G06K9/00
摘要:
Systems and methods are described for face recognition using discriminatively trained orthogonal rank one tensor projections. In an exemplary system, images are treated as tensors, rather than as conventional vectors of pixels. During runtime, the system designs visual features—embodied as tensor projections—that minimize intraclass differences between instances of the same face while maximizing interclass differences between the face and faces of different people. Tensor projections are pursued sequentially over a training set of images and take the form of a rank one tensor, i.e., the outer product of a set of vectors. An exemplary technique ensures that the tensor projections are orthogonal to one another, thereby increasing ability to generalize and discriminate image features over conventional techniques. Orthogonality among tensor projections is maintained by iteratively solving an ortho-constrained eigenvalue problem in one dimension of a tensor while solving unconstrained eigenvalue problems in additional dimensions of the tensor.