An improved detection algorithm of face with combining adaboost and SVM

This paper proposes a face detection method by combining SVM into the traditional face detection algorithm named AdaBoost. This method adopts SVM classifier instead of traditional AdaBoost classifier based on AdaBoost cascade framework. To get SVM classifier, extract several Haar-like features with the strongest classification ability in the process of training SVM classifier. To ensure the generalization capability of classifier classify validation set, and using the penalty factor setting with focus makes SVM classifier pay more attention to the face samples, while the training samples reached a high goodness of fit. At the same time, this thesis improves the extraction method of Haar-like feature. Finally, using Matlab simulation test the effectiveness of the algorithm. The experiments show that the improved detection algorithm of face with combining AdaBoost and SVM reduces the amount of computation and improve the detection rate.