Low-resolution face recognition method based on active discriminative cross-domain alignment

The invention discloses a low-resolution face recognition method based on active discrimination cross-domain alignment, and the method specifically comprises the steps: constructing an HR image set and an LR face image set, selecting a source domain sample from the LR face image set, forming a source domain sample set, and enabling the remaining LR face images to form a target domain sample set; meanwhile, the statistical distribution difference between source domain samples and target domain samples is reduced; constructing a discrimination alignment moment; establishing a linear transformation relationship between source domain samples and target domain samples; and constructing and solving a target function, calculating a source domain and standard domain sample transformation matrix, and deducing a category label of the face transformation feature of the target domain by using a nearest neighbor classifier. According to the method, the face feature space of the source domain and the face feature space of