| Summary: | 碩士 === 國立臺灣科技大學 === 電子工程系 === 107 === Facial expression recognition (FER) is a significant task for the machines to understand human emotions. However, traditional approaches need numerous different hand-crafted features which are difficult to design to adapt different situations. Deep learning is recently being adopted to solve FER problem because of its high accuracy. The proposed method adopted the deep learning architecture and further migrate the architecture to an embedded system. By migrating the proposed method to embedded systems can bring more applications to real world, such as analyzing the emotions of mobile users or collecting the users’ reactions to advertisements. To address the small dataset and extremely data imbalanced situation, we adopted data augmentation to increase the training samples, and class weight balancing during training to avoid the model to be dominated by the majority categories. Unlike most methods required high computation costs, such as a high-end CPU, and a GPU; we designed a mobile application for real-time facial expression recognition, and the average runtime is about 10-15 frames per second with the average accuracy at 52.25%.
|
|---|
