Abstract
Landmarking can be formalised as calculating the Maximum A-posteriori Probability (MAP) of a set of land-marks given an image (texture) containing a face. In this paper a likelihood-ratio based landmarking method is extended to a MAP-based landmarking method. The approach is validated by means of experiments. The MAP approach turns out to be advantageous, particularly for low quality images, in which case the landmarking accuracy improves significantly.
Original language | English |
---|---|
Title of host publication | BIOSIGNALS 2009 |
Subtitle of host publication | Proceedings of the 2nd International Conference on Bio-Inspired Systems and Signal Processing |
Pages | 12-17 |
Number of pages | 6 |
DOIs | |
Publication status | Published - 21 Jul 2009 |
Event | International Conference on Bio-Inspired Systems and Signal Processing 2009 - Porto, Portugal Duration: 14 Jan 2009 → 17 Jan 2009 http://www.biosignals.biostec.org/Biosignals2009/ |
Conference
Conference | International Conference on Bio-Inspired Systems and Signal Processing 2009 |
---|---|
Abbreviated title | BIOSIGNALS 2009 |
Country/Territory | Portugal |
City | Porto |
Period | 14/01/09 → 17/01/09 |
Internet address |
Keywords
- Biometrics
- Face recognition
- Landmarking