Robust Face Detection Using the Hausdorff Distance
AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
Experiments with Classifier Combining Rules
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Robust Real-Time Face Detection
International Journal of Computer Vision
An introduction to ROC analysis
Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Reliable Face Recognition Methods: System Design, Implementation and Evaluation (International Series on Biometrics)
Comparative testing of face detection algorithms
ICISP'10 Proceedings of the 4th international conference on Image and signal processing
Machine Vision and Applications
| Hi-index | 0.00 |
In this paper, a method of combining face detectors is proposed, which is based on the geometry of the competing face detection results. The main idea of the method consists in finding groups of similar face detection results obtained by several algorithms and further averaging them. The combination result essentially depends on the number of algorithms that have fallen in each of the groups. The experimental evaluation of the method is based on seven algorithms: Viola-Jones (OpenCV 1.0), Luxand © FaceSDK, Face Detection Library, SIFinder, Algorithm of the University of Surrey, FaceOnIt, Neurotechnology © VeriLook. The paper contains practical results of their combination and a discussion of future improvements.