Deception detection in videos using the facial action coding system

Facts are important for making decisions in every situation, which is why it is important to catch deceptive information before it can cause any harm. Deception detection in videos has gained traction in recent times for its various real-life applications. In our approach, we extract facial Action Units (AUs) using the Facial Action Coding System (FACS) from the Real-Life Trial dataset. Those AUs are used as parameters for training a deep learning model, specifically, Long Short-Term Memory (LSTM). Training the deep learning model in such a way provided one of the best results for facial-only approaches to deception detection. We also tested cross-dataset validation using the Real-Life Trial dataset, the Silesian Deception Dataset, and the Bag-of-lies Deception Dataset which has not yet been attempted by anyone else. We tested and compared all datasets amongst each other individually and collectively using the same deep learning training model. The results showed that adding different datasets to train the deep learning model worsened the accuracy of the model. One of the primary reasons for the decline in accuracy can be attributed to the nature of all datasets being different from one another.