Adaboost-kNN for dynamic emotion recognition

— K-nearest Neighbor based adaptive boosting (AdaBoost-KNN) is proposed for emotion understanding in human-robot interaction (HRI), where the real-time dynamic emotion is recognized according to facial expression. It can make robots capable of understanding human emotions and make HRI run smoothly. The Candide-3 model was adopted to extract the two-dimensional coordinate values of the key points of facial emotion, as the basis for emotion classification. The emotion classification is based on AdaBoost-KNN, which sets up seven basic KNN classifier. Then it iterates seven times to update the weight of samples, and combines the weak classifier with coefficient to establish the final classifier. Finally, the performance of the proposal is verified by using K-fold cross validation. Results show that the proposal achieves higher accuracy than that of a single KNN.