Real-time automatic face tracking using adaptive random forests
Tracking is treated as a pixel-based binary classification problem in this thesis. An ensemble strong classifier obtained as a weighted combination of several random forests (weak classifiers), is trained on pixel feature vectors. The strong classifier is then used to classify the pixels belonging t...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en |
| Published: |
McGill University
2010
|
| Subjects: | |
| Online Access: | http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=95172 |