A micro-expression recognition algorithm based on feature enhancement and attention mechanisms

In recent years, facial micro-expression recognition based on deep learning technology has become an important research hotspot. These techniques have been used by researchers in psychology, computer vision, and security to make breakthroughs. However, the proposed algorithm for micro-expression recognition faces some challenges in practical application. For example, the VGGMag method uses only one feature for micro-expression recognition, while the network cannot extract more useful features. The STRCN method does not focus on the key parts of facial micro-expressions, so that all parts of the face contribute equally to the micro-expression recognition model. A micro-expression recognition algorithm based on feature enhancement and attention mechanisms (FEAM) is proposed to further improve the recognition rate of micro-expressions. Firstly, the FEAM method designs a feature extraction module to extract micro-expression features and LBP image features, which preserves the texture information of the face. Secondly, the network constructs a feature augmentation module to highlight facial landmark points of faces as a way to increase the surrounding pixel weights. And then, the model designs the attention module to generate the attention correlation matrix of LBP and enhanced feature maps using the attention mechanism, which allows the network to pay more attention to the changes of features around the eyes and mouth of the face. Finally, the feature maps are input to the classification module for recognition. FEAM method is evaluated on three micro-expression datasets, and advanced results are obtained. The experimental results show that the proposed model FEAM can achieve state-of-the-art results compared to other models.