Many deep learning-based methods have been suggested in recent years to improve facial expression recognition performance, but they are unable to extract the small facial changes in skin textures, such as wrinkles and furrows, which indicate changes in expression. We put forward an attention mechanism-based Convolutional Neural Network (CNN) for face expression recognition to get around this issue. The attention module, classification module feature extraction module and the reconstruction module make up the architectures four components. The feature extraction module, which consists of two distinct CNN processing streams-one for raw images and the other for Local Binary Pattern (LBP) feature maps. The LBP features extract image texture data before capturing the minute facial movements, which can enhance network efficiency. The neural network can pay more attention to useful characteristics by using an attention mechanism. To improve the attention model and produce improved results, we combine LBP features and convolutional features. We use the CK+ and Oulu-CASIA datasets to test the proposed methodology. The experimental findings show that the suggested method is workable and efficient.