CK+48 Emotion Detection Image Dataset

This dataset contains 48×48 grayscale facial expression images organized into emotion categories for research in facial expression recognition and emotion analysis. The original CK+ dataset was developed by Jeffrey F. Cohn and Takeo Kanade and has been widely adopted as a benchmark in computer vision and emotion recognition studies. It can be used for training and evaluating machine learning and deep learning models in computer vision and affective computing applications.