Gabor filtering and joint sparsity model-based face recognition method

The invention discloses a Gabor filtering and joint sparsity model (JSM)-based face recognition method, which comprises the following steps of: first filtering face images in a Gabor filtering way to extract characteristics insensitive to light and expressions; then extracting common parts and the sum of private parts of each type of trained image by taking the extracted Gabor characteristics as the input of a JSM; and finally constructing a dictionary by utilizing the extracted common parts and the sum of the private parts, obtaining the sparse representation of a face image to be recognized on the constructed dictionary by adopting a spare representation classification (SRC) method, and obtaining a recognition result according to a sparse representation coefficient. The method has the advantages that each type of trained face image can be effectively presented by utilizing only two characteristic images, so that the size of a storage space is reduced; and due to the introduction of Gabor filtering, the method has high robustness for the changes of face expressions and light.