A Novel Face Detection Algorithm Based on PCA and Adaboost

摘要

This paper studies the feature based face detection algorithm. Based on the principal component analysis, feature vector space is extracted to construct weak classifier. Combined with Adaboost algorithm to construct the strong classifier, an algorithm for face detection is presented. The performance of the algorithm is tested based on MIT+CMU face database, the results show that the algorithm in the running time and detection accuracy is significantly better than the algorithm based on neural network and support vector machine algorithm.