Analyzing human emotion from facial expression based on Eigen face approach

The technique of Facial recognition makes it easy to use a person’s facial images to validate him in a secure system such as passport verification, criminal identification and for other authentication purposes. First, in order to detect the expression of human face, it is required to detect and recognize facial details such as eye, nose, lips, mouth etc. movements using an adequate classifier for expression recognition. In this work subtle facial expression recognition that uses Eigen face approach and Euclidean distance classifier. The proposed method uses certain techniques in pre-processing the image such as image lighting compensation, cropping the skin block region, converting the RGB image to grey scale image, and other noise removal techniques. PCA has been used for reducing the high dimensionality of the Eigen space of the image and then by projecting the test image upon the Eigen space. Different expression such as joy, sorrow, anger, disgust, sad and indifference can be identified using the Eigen face method. The Euclidean distance is calculated between the test image and mean of the Eigen faces of the training dataset and then the expressions are classified. The analysis of the simulation indicates the importance of the proposed work.