This paper presents emotion recognition models using facial expression features. By detecting the face in videos and extracting local characteristics (landmarks) to generate the geometric-based features to discriminate between a set of five emotion expressions (amusement, anger, disgust, fear, and sadness) for videos from BioVid Emo database. The classification operation is done using different machine learning models including random forest (RF), support vector machines (SVM), k-nearest neighbors (KNN) and recurrent neural network (RNN), then the evaluation operation is done to generate different discrimination rates that reached up to 82% to discriminate between anger and disgust emotions.
Machine learning algorithms
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL