Oulu-CASIA

该数据集是一个实验室控制的资料集，包含了80位受试者的视频序列，这些视频序列是通过可见光和近红外光同时捕捉的。该数据集仅考虑六种基本表情，并将数据集分为训练集和测试集，其中训练集包含80%的受试者，测试集包含剩余的20%受试者。该数据集的规模为80位受试者，任务是对近红外光下的面部表情进行识别。

This is a laboratory-controlled dataset containing video sequences from 80 subjects, which were simultaneously captured using visible light and near-infrared light. Only six basic facial expressions are considered in this dataset, which is divided into a training set and a test set: 80% of the subjects are included in the training set, while the remaining 20% constitute the test set. With a total of 80 subjects, the task of this dataset is facial expression recognition under near-infrared light.