Discriminative Manifold Learning In Face Recognition Applications

Human face is the most common visual part. Human face recognition has become not only a hot research topic in the field of artificial intelligence and model recognition, but also a most potential recognition technology by biometric characteristic for the merits of being natural, directly perceived, safe and convenient. However, due to the complexity of human face structure, the diversity of face expression and the changeable in face image formation process, computer face recognition technology is universally considered a challenging study topic. In a sense, it is commonly accepted that human face is a manifold structure. Face dataset is a non-linear manifold formed by some inner variables, such as illumination condition, face pose and facial expression. If some controlled variables can be seeked, space dimensionality could be reduced greatly.In recent years, manifold learning become a hot study topic in the field of artificial intelligence and model recognition. and its aim is to seek low-dimensional smoothy manifold in high-dimensional observation data space. Since Roweis and Saul put forward LLE algorithm in 2000, Tenenbaum and his collegues proposed Isomap algorithm, especially after Donoho discovered Isomap algorithm can obtain the potential prameter space of face image manifold, Zhang Changshui and his collegues found LLE algorithm applied to face recognition can bring out better recognition effects, face recognition research based on manifold learning is attracting more and more attention. This paper focuses on the application of manifold learning in human face recognition, and introduced two improved algorithms based on manifold learning used for face recognition, and each algorithm's effectiveness has been verified by experiments. The research work in this paper mainly includes the following several respects:1) In this paper we briefly introduce the classical linear feature extraction algorithms and some manifold learning algorithms. The classical linear feature extraction algorithms includes PCA,LDA; and the non-linear manifold learning algorithm includes Isomap,LLE,LE,LTSA. And also the advantage and disadvantage of the common manifold learning algorithms are introdued repectively.2) The improved Isomap algorithm based on Kernel Fisher Linear Discriminant Analysis (KFLD-lsomap) is presented. The KFLD-lsomap algorithm introdued the Kernel Fisher Linear Discriminant Analysis (KFLD) to find the optimal projection matrix instead of the Multi-Dimensional Scaling(MDS) for pattern classification. Experiments are carried out on ORL face database and Yale face database. Compared with KFLD-Isomap and other algorithms, KFLD-Isomap algorithm could overcome the change of facial expression,illumilation intensity and direction in some extent, so the face recognition rate is higher than other algorithms.3) The IMED-Isomap+DLDA algorithm is demonstrated lastly. The IMED-Isomap+DLDA algorithm manily based on IMage Euclidean Distance(IMED) and Direct Linear Discriminant Analysis(DLDA). Unlike the traditional Euclidean Distance,IMED takes into account the spatial relationships of pixels, therefore it is robust to small perturbation of images. Then Direct Linear Discriminant Analysis (DLDA) is used to replace Multi-Dimensinal Scaling(MDS). Compared the other algorithms, the experiments on ORL face database and the Yale face database show that the IMED-Isomap+DLDA enhances the ability of classication. In addition, the IMED-Isomap+DLDA obtains a better performance than other algorithms for face images classification with small noise and geometrical deformation.