Multi-Feature Fusion based Non Negative Matrix Factorization: Facial Expression Recognition from Imaging Sensors

摘要: Imaging sensors are widely used in HCI applications to capture images for facial expression recognition. The proccess involves extraction of features from captured and use machine learning algorithms like K-NN classification identify the specific expression. We propose here a recognition system based on non-negative matrix factorization (NMF). As parts more prominent express particular rather than whole faces NMF does part analysis, we interested analyse how works Facial Recognition. benchmark our CK+ JAFFE dataset. get significant result. In addition also WAPA OEPA this application. Our proposed is actually two types fusion method where counts all four name it as Weighted All Parts Accumulation (WAPA) algorithm. On otherhand, only most expressive each Optimal Expression-specific (OEPA). experiment shows outperform prevalent method.