6533b871fe1ef96bd12d0b85

RESEARCH PRODUCT

Real-time micro-expression analysis by artificial vision

subject

description

Human-computer interaction technologies focus more and more on the human being, whether it is on his identity, or on his physical and mental state. Significant progress has been made in the last few decades. However, the study of thoughts and emotions is still an underdeveloped field, but one that has begun to gain considerable interest. In this field, the analysis of facial expressions is the preferred treatment.Unlike a macro-expression, which is visible to the eye, a micro-expression is a type of involuntary facial expression that is extremely rapid and of very low intensity. The computer vision scientific community has been studying ways to automatically recognize micro-expressions using high-speed cameras and computer programs for several years. However, it is a difficult problem, due to the nature of these micro-expressions.Based on the latest technical advances in machine learning, we have proposed several treatments for recognizing micro-expressions on videos while focusing on the speed of execution and low memory requirements. Following the evolution of the literature, we first proposed improvements in the use of descriptors such as LBP-TOP, then we configured the structure of a convolutional neural network to make it more compact without losing accuracy.With results similar to current methods, we have significantly reduced memory and computational requirements. We have finally demonstrated the feasibility of running a complete system in real conditions that performs both detection and recognition of micro-expressions.