Emotion Recognition on large video dataset based on Convolutional Feature Extractor and Recurrent Neural Network
This work addresses emotion recognition for human-computer interaction, but it is incremental as it applies a hybrid deep learning approach to an existing large dataset.
The study tackled emotion recognition from video data by combining CNN and RNN models, achieving improved performance through dataset balancing with downsampling on the Aff-Wild2 dataset containing over sixty hours of video.
For many years, the emotion recognition task has remained one of the most interesting and important problems in the field of human-computer interaction. In this study, we consider the emotion recognition task as a classification as well as a regression task by processing encoded emotions in different datasets using deep learning models. Our model combines convolutional neural network (CNN) with recurrent neural network (RNN) to predict dimensional emotions on video data. At the first step, CNN extracts feature vectors from video frames. In the second step, we fed these feature vectors to train RNN for exploiting the temporal dynamics of video. Furthermore, we analyzed how each neural network contributes to the system's overall performance. The experiments are performed on publicly available datasets including the largest modern Aff-Wild2 database. It contains over sixty hours of video data. We discovered the problem of overfitting of the model on an unbalanced dataset with an illustrative example using confusion matrices. The problem is solved by downsampling technique to balance the dataset. By significantly decreasing training data, we balance the dataset, thereby, the overall performance of the model is improved. Hence, the study qualitatively describes the abilities of deep learning models exploring enough amount of data to predict facial emotions. Our proposed method is implemented using Tensorflow Keras.