Face Recognition Based on Improved Space Variant

The fusion of imaging model and differential geometric is used to research the recognition problem of blurred-image in this paper. According to some assumptions, the established subspace results from the convolution of an image with some complete orthonormal basis functions with a predefined maximum size. Therefore, we demonstrate that the corresponding subspace created from a clear image and its blurred version is equal under the ideal case of zero noise and properties of blur kernels. Then, the paper studies the application of invariance in direct face recognition algorithm. We view the subspaces as points on the Grassmann manifold and adopt the subspace representation method to perform recognition of blurred image. In addition, we also provide the recognition rate of blurred image, where the blur variable is both homogeneity and space-variant. Finally, simulation experiment results show that the proposed algorithm can effectively improve the accuracy, and achieve a higher face recognition rate in comparison with the existing face recognition algorithms.