| Presentation | 2001/3/15 Extended Virtual Subspace Method For Face Recognition Independent of Pose and Illumination Kunihiro Nakagawa, Takeshi Shakunaga, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This papaer discusses face recognition independent of both its pose and illumination. We have proposed the virtual subspace method for face recognition under varying illumination, in which a virtual subspace is constructed from no less than one images by synthesizing a set of virtual images in a variety of lighting conditions. This paper extends the method to cover any face poses. For the purpose, a canonical 3d face model is introduced for pose transformation of any face images to canonical poses. In the registration stage, the virtual subspace is constructed in the canonical eigenspace using the transformed image. In the recognition stage, distances are measured between virtual subspaces and the transformed image. Experimental results show the effectiveness of the proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | virtual subspace method / face recognition / pose transformation / canonical 3d face model |
| Paper # | PRMU2000-214 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2001/3/15(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Extended Virtual Subspace Method For Face Recognition Independent of Pose and Illumination |
| Sub Title (in English) | |
| Keyword(1) | virtual subspace method |
| Keyword(2) | face recognition |
| Keyword(3) | pose transformation |
| Keyword(4) | canonical 3d face model |
| 1st Author's Name | Kunihiro Nakagawa |
| 1st Author's Affiliation | Department of Information Technology Okayama University() |
| 2nd Author's Name | Takeshi Shakunaga |
| 2nd Author's Affiliation | Department of Information Technology Okayama University |
| Date | 2001/3/15 |
| Paper # | PRMU2000-214 |
| Volume (vol) | vol.100 |
| Number (no) | 701 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |