A Human Facial Expression Recognition Model Based on Eigen Face Approach

Emotion recognition through facial expression detection is one of the important fields of study for human-computer interaction. To detect a facial Expression one system need to come across various variability of human faces such as colour, posture, expression, orientation, etc. To detect the expression of a human face first it is required to detect the different facial features such as the movements of eye, nose, lips, etc. and then classify them comparing with trained data using a suitable classifier for expression recognition. In this research, a human facial expression recognition system is modelled using eigenface approach. The proposed method uses the HSV (Hue-Saturation-Value) colour model to detect the face in an image. PCA has been used for reducing the high dimensionality of the eigenspace and then by projecting the test image upon the eigenspace and calculating the Euclidean distance between the test image and mean of the eigenfaces of the training dataset the expressions are classified. A generic dataset is used for training purpose. The gray scale images of the face is used by the system to classify five basic emotions such as surprise, sorrow, fear, anger and happiness.