The present disclosure provides a method and apparatus for expression recognition, which is applied to the field of image processing. The method includes acquiring a three-dimensional image of a target face and a two-dimensional image of the target face, where the three-dimensional image includes first depth information of the target face and first color information of the target face, and the two-dimensional image includes second color information of the target face. A first neural network classifies an expression of the target face according to the first depth information, the first color information, the second color information, and a first parameter to the target face. The first parameter includes at least one facial expression category and first parameter data for identifying an expression category of the target facial. The disclosed method and device can accurately recognize facial expressions under different facial positions and different illumination conditions.