Admissions Open
Admissions Open
Human Machine Interaction has gained significant attention in the previous years. The communication through facial expression plays a vital role in the interaction since the expressions convey more information than spoken words and it allows to recognize the emotions without wearing sensors and monitoring devices. So it is important to classify the emotions correctly. In this paper, we have proposed an effective framework for Emotion Recognition using Facial Expressions which recognizes 96.2% of emotions accurately. Voila Jones Algorithm is used for face detection followed by splitting the face in parts which are dominant for expressions and applying Gauss Filtering to these parts. Combination of HOG and LBP features is used to extract the features. PCA is used for dimensionality reduction and these features are classified using Canberra Distance Classifier. The framework performs well on JAFFE Dataset and gives promising results.