中文摘要：

本文以情绪认知交互的E-Learning系统中的学习者表情识别为背景，在Adaboost算法中引入了分类风险系数，并在每次迭代权值更新后的权值归一化过程中，将正负例样本分开进行权值归一化处理，保证了算法能始终给予正例样本更多的重视．最终将基于肤色和改进的Adaboost算法相结合用于E-Learning情境中的学习者人脸检测，取得了较好的实验效果．为后续的表情特征提取工作提供了重要的信息．

英文摘要：

This Paper is with the background knowledge of learners＇expression recognition in emotion recognition interactive E-Leaming, the Adaboost algorithm is introduced in the classification of risk factors. Ensure that the algorithm can always give more attention to the positive samples. This paper is based on the skin and improved Adaboost arithmetic, which uses for detecting the face of learners in E-Learning. This method has a better test results. It is provided important information to follow-up expression feature extraction.