Humans often have different moods and facial expressions changes accordingly. Human emotion recognition plays a very important role in social relations. The automatic recognition of emotions has been an active analysis topic from early eras. In this deep learning system user’s emotions using its facial expression will be detected. Real-time detection of the face and interpreting different facial expressions like happy, sad, angry, afraid, surprise, disgust, and neutral. etc. This system can detect six different human emotions. The trained model is capable to detect all the mentioned emotions in real-time. An automatic facial expression Recognition system has to perform detection and site of faces during a cluttered scene, facial feature extraction, and facial expression classification. The facial expression recognition system is enforced victimization of Convolution Neural Network (CNN). A CNN model is trained on FER2013 dataset. FER2013 Kaggle faces expression dataset with six facial features labels as happy, sad, surprise, fear, anger, disgust, and neutral is used throughout this project. Compared to the other datasets, FER has more variation in the images, including face occlusion, partial faces, low-contrast images, and eyeglasses. This system has ability to monitor people emotions, to discriminate between emotions and label them appropriately and use that emotion information to guide thinking and behaviour of particular person.
- Business can process images, and videos in real-time monitoring
- Automation of Video Analytics