Micro-expression is usually characterized by short duration and small action range, and the existing general expression recognition algorithms do not work well for micro-expression. As a feature extraction method, non-negative matrix factorization can decompose the original data into different components, which has been successfully applied to facial recognition. In this paper, local non-negative matrix factorization is explored to decompose micro-expression into some facial muscle actions, and extract features for recognition based on apex frame. However, the existing micro-expression datasets fall short of samples to train a classifier with good generalizability. The macro-to-micro algorithm based on singular value decomposition can augment the number of micro-expressions, but it cannot meet non-negative properties of feature vectors. To address these problems, we propose an improved macro-to-micro algorithm to augment micro-expression samples by manipulating the macro-expression data based on local non-negative matrix factorization. Finally, several experiments are conducted to verify the
effectiveness of the proposed scheme which results show that it has a higher recognition accuracy for micro-expression compared with the related algorithms based on CK+/CASME2/SAMM datasets.