Department of Artificial Intelligence, Kyungpook National University, Daegu 41566, Korea.
Sensors (Basel). 2022 Sep 3;22(17):6671. doi: 10.3390/s22176671.
Facial expressions are divided into micro- and macro-expressions. Micro-expressions are low-intensity emotions presented for a short moment of about 0.25 s, whereas macro-expressions last up to 4 s. To derive micro-expressions, participants are asked to suppress their emotions as much as possible while watching emotion-inducing videos. However, it is a challenging process, and the number of samples collected tends to be less than those of macro-expressions. Because training models with insufficient data may lead to decreased performance, this study proposes two ways to solve the problem of insufficient data for micro-expression training. The first method involves -step pre-training, which performs multiple transfer learning from action recognition datasets to those in the facial domain. Second, we propose Décalcomanie data augmentation, which is based on facial symmetry, to create a composite image by cutting and pasting both faces around their center lines. The results show that the proposed methods can successfully overcome the data shortage problem and achieve high performance.
面部表情分为微表情和宏表情。微表情是强度较低的情绪表现，持续时间约为 0.25 秒，而宏表情持续时间可达 4 秒。为了提取微表情，要求参与者在观看诱发情绪的视频时尽可能地抑制自己的情绪。然而，这是一个具有挑战性的过程，收集的样本数量往往少于宏表情。因为用数据不足的模型进行训练可能会导致性能下降，所以本研究提出了两种解决微表情训练数据不足的方法。第一种方法涉及 -step 预训练，它从动作识别数据集多次进行迁移学习到面部领域的数据集。其次，我们提出了基于面部对称性的 Décalcomanie 数据增强，通过沿着中心线剪切和粘贴两个面部来创建合成图像。结果表明，所提出的方法可以成功克服数据短缺问题并实现高性能。
