Face Recognition Based on a Combination of Increasing Virtual Samples and Kernel Principal Component Analysis

In pattern recognition such as face recognition, the recognition result is not only limited by the quality and quantity of samples, but also limited by the extracted principal components. For improving the quality and quantity of training samples and for extracting more efficient principal components, this paper presents a recognition method combing the increased virtual samples and kernel principal component analysis (KPCA), which doubly weakens the influence of nonlinear factors on face recognition. New database is generated with the pose-changed and the mirror-like virtual images. Then KPCA is used for dimension reduction and feature extraction. The shortest Euclidean distance is applied to measure similarity. A series of experiments are conducted in the ORL and YALE face database and the experimental results show the efficiency of the proposed method.