Facial expression classification
Zhuoyue Ren · Highlights in Science Engineering and Technology · 2023
At present, emotion classification has become a hot topic in artificial intelligence pattern recognition. The facial expression recognition (FER) is indispensable for computers to understand the emotional information conveyed by expressions. In the past, using traditional features to extract and classify facial expressions has not achieved satisfactory accuracy, so the classification of facial emotions is still a challenge. The model used in the paper is an existing one - MINI_XCEPTION, the dominant framework for CNNs that extracts features from images to identify and classify seven facial emotions. The model was trained on a dataset of people’s facial expressions (Kaggle). This model has a significant improvement over the previous model.