Learning discriminative features for expressions from facial images captured in the wild is a non- trivial task due to intra-class variations and inter-class similarities. Furthermore, background clutter, illumination changes, large pose variations, and partial or full occlusions make it more challenging. The goal of this project is to design and develop a computer vision system that can classify facial expressions. Such a system can have several real-world applications. For example, expressions can be useful for Human-Computer Interaction based recommendation systems to determine whether to push product information or not. It can also be used to determine the psychological state of a person during online interviews.
The dataset selected for this task is the Expression in-the-Wild (ExpW)1 dataset. The dataset can be downloaded from the following link: https://drive.google.com/drive/folders/1SDcI273EPKzzZCPSfYQs4alqjL01Kybq The Expression in-the-Wild (ExpW) dataset is for facial expression recognition and contains 91,793 faces manually labeled with expressions (Figure 1). Each of the face images is annotated as one of the seven basic expression categories: “angry (0)”, “disgust (1)”, “fear (2)”, “happy (3)”, “sad (4)”, “surprise (5)”, or “neutral (6)”.