Face detection based on improved AdaBoost algorithm in E-Learning

Abstract

This paper is based on the background of learners' expression recognition in emotion recognition interactive E-Learning. This paper aims at time-consuming of training samples and weights degradation two problems of traditional AdaBoost algorithm, proposes a decile eigenvalue AdaBoost algorithm and joins FPR (False Positive Rate) in this algorithm. The experiments use improved AdaBoost algorithm in E-Learning face detection achieved good effect, and the results provide good conditions for the follow-up E-Learning expression feature extraction.