Real Time Face Emotion Detection with CNN
摘要
A model that uses the Convolutional Neural Network deep learning algorithm to identify emotions on a person's face in real time is proposed in order to further the technology of recognition of facial expression used in machine learning and artificial intelligence (CNN). In order to find the face in the picture and register it in the face detection stage, image pre- processing is first carried out, in which a grayscale image is produced from the input image. During the extraction of face features, a feature vector is created once the facial features have been extracted. The facial expression that is recognized during the emotion classification stage is categorized into one of a human's seven primary emotions. With the use of CNN, the proposed model has been observed to provide great accuracy and improved performance.