A company wants a model that can be used in job interviews to detect the emotional expressions of the candidates and their reactions to the questions. The goal is to detect emotional expressions from a webcam or video, then measure how many times each emotional expression appeared.
The dataset is called Face expression recognition dataset, and consists of 48x48 pixel grayscale images of faces. The faces have been automatically registered so that the face is more or less centered and occupies about the same amount of space in each image. The dataset contains 7 files representing emotional expressions, which are: Angry, Disgust, Fear, Happy, Sad, Surprise, and Neutral.
You can find and download the dataset from here
- Detect emotional expressions.
- Measure how many times each emotional expression appeared.
- Measure the percentage of each emotional expression that appeared.