Abstract:
Machine automated face recognition has gained significant importance due to its scientific challenges and its potential applications. However, most of the systems designed to date can only successfully recognize faces when images are obtained under constrained conditions. The success of face recognition systems rely on a variety of information in images of human faces such as pose, facial expression, occlusion and presence or absence of structural components. The proposed model targets an approach for the recognition of expression variant faces since there are very few face recognition solutions to address this problem and this is a key research area in face recognition. This model proposes an approach to face recognition where the facial expression in the training image and in the testing image diverge and only a single sample image per class is available to the system. The input to the system is a frontal face image with neutral expression and identical background where the subjects' hair is tied away from the face. The proposed model is based on Principal Component Analysis approach. This approach has been applied on a set of images in order to extract a set of Eigen-images known as Eigen faces and weights of this representation are used for recognition. For the classification task, distance metric Euclidean Distance has been used to find the distance with the weight vectors associated with each of the training images. When tested with eight subjects and six basic expressions the overall recognition rate was 89%, for trained faces.
