Abstract
In this paper, we introduce a registration method for side-view face recognition that is suitable for home safety applications. We use cameras attached at door posts, and recognize people as they pass through doors to estimate their location in the house. First, we present a new database that is collected using this setup, where we use side cameras and ambient light. We recorded videos of 14 people that pass through doors in 18 different paths. Next, we propose our recognition method where we automatically find the profile to register the face images. By applying hierarchical clustering we detect the frames that include falsely detected profiles and pose variations, and automatically remove them from the video sequence to improve our results. After registering, we find the nose tip, apply recognition based on profiles, and analyze our results.
| Original language | English |
|---|---|
| Title of host publication | 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux |
| Place of Publication | Enschede |
| Publisher | Werkgemeenschap voor Informatie- en Communicatietheorie (WIC) |
| Pages | 220-227 |
| Number of pages | 8 |
| ISBN (Print) | 978-90-365-3383-6 |
| Publication status | Published - May 2012 |
| Event | 33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012 - Boekelo, Netherlands Duration: 24 May 2012 → 25 May 2012 Conference number: 33 |
Conference
| Conference | 33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012 |
|---|---|
| Country/Territory | Netherlands |
| City | Boekelo |
| Period | 24/05/12 → 25/05/12 |
Keywords
- SCS-Safety
- IR-84167
- METIS-296303
- EWI-23079