Facial Emotion Recognition in Videos using HOG and LBP

Abstract

Emotions are found using verbal and non-verbal cues by analyzing voices and facial expressions. Monitoring emotional patterns of human is gaining importance in predicting the mood of a person. Facial emotion recognition is the process of detecting and recognizing different types of emotions in humans using facial expressions. The various steps include detection of the face and its landmarks, feature extraction of facial landmarks, and emotional state classification. The Haar cascading approach is used to detect different facial components such as eyes, mouth, and nose in an image. Facial features are analyzed using Histogram of Gradients (HOG) and Local Binary Pattern (LBP). The resultant feature vector is formed from the feature points. The three emotional states namely happy, sad and angry are classified using neural network classifier. The new feature points of test data are compared against trained data and their corresponding label values are displayed as the output for emotion recognition with the accuracy of 87% and 64% is being achieved using HOG and LBP techniques.