Microexpression Recognition based on Improved Robust Principal Component Analysis and Texture Feature Extraction

Micro-expression can reflect the emotional information that humans can hardly conceal. There are three main characteristics: short duration, low intensity and local movement. From these characteristics it can be seen that the motion of the microexpression is sparse. For sparse micro-expression movement, a robust principal component analysis (RPCA) was proposed to extract subtle micro-expression motion information. Using improved Edge Direction Histogram (EOH) algorithm and Binary Gradient Contours (BGC) algorithm to extract local texture features can solve the problem of spatio-temporal domain and obtain high recognition accuracy. Experiments on the SMIC database show that the proposed algorithm has better performance.