Identifying Human Emotion is important in facilitating communication and interactions between individuals. They are also used as an important mean in studying behavioral Science and in studying Psychological changes. There are many applications which uses Facial Expression to evaluate human nature, their feelings, judgment, and opinion. Recognizing Human Facial Expression is not a simple task because of some circumstances due to illumination, facial occlusions, face color/shape etc. Since face is the prime source for recognizing human emotion, this paper will provide the best method that can be adopted for non-invasive real time emotion detection. This paper involves a comparative analysis of facial expression recognition techniques using the classic machine learning algorithms-KNN, SVM, Ensemble classifiers. The machine learning algorithms have been implemented on JAFFE IMAGE DATABASE on MATLAB 2016a. Successful and satisfactory results have been obtained giving the future researchers in this field an insight into which technique to be used when, to get the desired results. © BEIESP.