Abstract: Distance education network learners can easily feel tired in the learning process due to the long-term lack of emotional interaction, and the learning fatigue usually presents by the eye state. To monitor the remote intelligent teaching system effectively, a kind of recognition algorithm of eye state in learning fatigue state is put forward based on Gabor wavelets and HMM. Due to the different characters of the eye openness degree in normal study, fatigue and confusion, the three learning states, the algorithm conducts gray difference processing to the eye image using Laplacian in YCbCr color space. It selects the second-dimension Gabor kernel function, constructing 48 most optimal filters, for 48 characteristic values. The 48 characteristic values will generate 48 characteristic vectors, and later HMM will be used to recognize the eye state of the eye by the set of observation sequence O formed by the characteristic vectors of the eye state image. The experimental result shows that the network learning fatigue recognition rate of this algorithm reaches 95.68%, with good robustness.

Key words: learning fatigue, E-learning, Gabor wavelet, Hidden Markov Model（HMM）

摘要： 远程教育的网络学习者在学习过程中由于长期缺少情感互动容易导致学习疲劳，而学习疲劳状态往往通过眼部状态表现出来,为了对远程智能教学系统进行有效的监控，提出了一种基于Gabor小波和HMM的学习疲劳眼部状态识别算法。该算法针对网络学习者的正常学习、疲劳和疑惑三种学习状态下的眼睛张开程度有一定的区别的特点，在YCbCr颜色空间用拉普拉斯算子对眼部图像进行灰度差的处理，选择二维Gabor核函数，构造48个最优滤波器，获取48个特征值，这48个特征值生成48个特征向量，用HMM对眼部状态图像的特征向量形成的一组观测序列[O]进行眼部状态识别。实验结果表明，该算法对网络学习的疲劳度识别率达到95.68%，具有良好的鲁棒性。

关键词: 学习疲劳, 网络学习, Gabor小波, 隐马尔可夫模型