The main work of this thesis is to determine whether a given image is a human face picture by using the eigenface approach-a face recognition method based on PCA (Principal Component Analysis). The approach calculate eigenvector (or eigenface) from the training set to obtain a subspace spanned by the eigenfaces, and then project the face images in training set onto the subspace. When detecting faces, the two-dimensional face image is proiected onto the face space and the Euclidian distance between the image and the subspace is computed. If ...