As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
To improve the performance of face recognition with only one sample per person, a novel method of face recognition based on virtual images with multi-pose and micro expressions is presented here. At first, the quadratic function is used to create the virtual images as training samples, so as to enhance the classification information of single training sample. Then the effective discriminative features are extracted through the Bidirectional two dimensional PCA in the residual space. The influence of different illumination on face recognition was cut down effectively. Experiments on ORL and Yale dataset show the effectiveness of the proposed method and the face recognition rate is improved.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.