Facial Expression Recognition Using Enhanced Convolution Neural Network with Attention Mechanism

Facial Expression Recognition (FER) has been an interesting area of research in places where there is human-computer interaction. Human psychology, emotions and behaviors can be analyzed FER. Classifiers used FER have perfect on normal faces but found to constrained occluded faces. Recently, Deep Learning Techniques (DLT) gained popularity applications real-world problems including recognition human emotions. The face reflects emotional states intentions. An expression the most natural powerful way communicating non-verbally. Systems which form communications between two are termed Machine Interaction (HMI) systems. improve HMI systems as expressions convey useful information observer. This paper proposes a scheme called EECNN (Enhanced Convolution Neural Network with Attention mechanism) recognize seven types satisfying results its experiments. Proposed achieved 89.8% accuracy classifying images.