A double-dictionary and multi-feature fusion decision-making face expression recognition method based on sparse representation

摘要: The invention discloses a double-dictionary and multi-feature fusion decision facial expression recognition method based on sparse representation, the comprises steps of firstly, extracting features from an expression-free face image sample specific sample, constructing nominal dictionary feature according to features; Image tobe identified, corresponding features, performing coding by adopting dictionary, combining coefficient result with obtain reconstructed subtracting before after reconstruction only containing information, sparsecoding vector; training auxiliary dictionaries for different types basis dictionaries, classification judgment vectors calculated representation results various obtaining final identification in voting mode. can effectively overcome influence face, illumination, shielding other changes recognition.