Micro-expression recognition method based on reconstructed cross-domain video generative adversarial network model

The invention relates to a micro-expression recognition method based on a reconstructed cross-domain video generative adversarial network model. The micro-expression recognition method comprises the following steps: (1) respectively decomposing macro-expressions and micro-expressions into expression types and identity contents; (2) combining the identity content of the macro-expression with the expression type of the micro-expression to obtain a generated micro-expression of the macro-expression identity; combining the identity content of the micro-expression with the expression type of the macro-expression to obtain the generated macro-expression of the micro-expression identity; (3) decomposing into expression types and identity contents again; combining the identity content obtained bydecomposing the micro-expression of the generated macro-expression identity with the expression type obtained by decomposing the macro-expression of the generated micro-expression identity; generatinga macro-expression, and c