Emotion recognition using Principal Component Analysis with Singular Value Decomposition

Emotion recognition plays vital role in Human Computer Interface. This paper focuses on facial expression to identify seven universal human emotions such as, happy, disgust, neutral, anger, sad, surprise and fear. This is carried out by trying to extract unique facial expression features among emotions using Principal Component Analysis with Singular Value Decomposition and Euclidean Distance Classifier. Using public database Japanese Female Facial Expression (JAFFE) recognition is obtained nearly 78.57%. Recognition rate and Accuracy of various expressions using Principal Component Analysis alone and Principal Component Analysis with Singular Value Decomposition is compared.