Making large-scale support vector machine learning practical
Advances in kernel methods
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic Vision: From Images to Face Recognition
Dynamic Vision: From Images to Face Recognition
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Training Support Vector Machines: an Application to Face Detection
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Implementation of a Modular Real-Time Feature-Based Architecture Applied to Visual Face Tracking
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Multi-View Face Detection under Complex Scene based on Combined SVMs
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Handbook of Face Recognition
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Adaptive weighting of local classifiers by particle filters for robust tracking
Pattern Recognition
Face detection for video summary using illumination-compensation and morphological processing
Pattern Recognition Letters
Face Detection Based on Facial Features and Linear Support Vector Machines
ICCSN '09 Proceedings of the 2009 International Conference on Communication Software and Networks
Fast frontal-view face detection using a multi-path decision tree
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
A Bayesian discriminating features method for face detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
This paper proposes a method combining local SVM classifiers and a Kalman filter to track faces in color video sequences, which is referred to as the Dynamic Local Support Vector Tracker (DLSVT). The adjacent locations of the target point are predicted in a search window, reducing the number of image regions that are candidates to be faces. Thus, the method can predict the object motion more accurately. The architecture presented good results for both indoor and outdoor unconstrained videos, considering multi-view scenes containing partial occlusion and bad illumination. Moreover, the reduction of the image area in which the face is searched for results in a method that is faster, besides being precise.