Research On Face Recognition Baesed On Pincipal Component Analysis

Biometrics is a kind of science and technology using individual physiological or behavioral characteristics to verify identity. It provides a highly reliable and robust approach to the identity recognition. Automatic face detection and recognition is one of the most attention branches of biomerics and it is also the one of the most active and challenging tasks for image processing, pattern recognition and computer vision. It is widely applied in commercial and law area, such as mug shots retrieval, real-tine video surveillance in security system and cryptography in bank and so on. The main research works and contributions are as the following.First, the research content, approach and development are emphasized. The research status is introduced. The technology of the face detection and recognition are summarized. And the paper describes face preprocessing in detail which is and important step in the face recognition. The face preprocessing methods we adopt are based on image processing techniques. The main purpose is to get the standardized facial images, and to eliminate the impact of illumination to some extent. In this paper, several key preprocessing methods are introduced, such as geometry normalization, gray-scale normalization and images binary-conversion.Principal Component Analysis (PCA) face recognition methods as the foundation of the K-L transformation is the most superior in the image compression [1].By using PCA, the dimension of the input is reduced while the main components are maintained. The major idea of PCA is to decompose a data space into a linear combination of a small collection of bases. In the face-recognition literature, the eigenvectors can be referred to as eigenfaces[2]. The probe is identified by first projection to all gallery images. We denote a probe. A probe is comparing the projection to all gallery images, and it causes around the compression the mean error to be youngest. But in the PCA-based face recognition technique, the 2D face image matrices must be previously transformed into 1D image vectors. The resulting image vectors of faces usually lead to a highdimensional image vector space, where it is difficult to evaluate the covariance matrix accurately due to its large size and the relatively small number of training samples.Instead of PCA, a straightforward image projection technique, called two-dimensional principal component analysis (2DPCA), is developed for image feature extraction.2DPCA is based on 2D matrices rather than 1D vectors. That is, the image matrix does not need to be previously transformed into a vector. Instead, an image covariance matrix can be constructed directly using the original image matrices. In this paper, we discusses the two method, and a series of experiments were performed on the ORL face image databases. The recognition rate across all trials was higher using 2DPCA than PCA. The experimental results also indicated that the extraction of image features is computationally more efficient using 2DPCAthan PCA.