Exploring the Feasibility of Face Video Based Instantaneous Heart-Rate for Micro-Expression Spotting

Abstract

Facial micro-expressions (ME) are manifested by human reflexive behavior and thus they are useful to disclose the genuine human emotions. Their analysis plays a pivotal role in many real-world applications encompassing affective computing, biometrics and psychotherapy. The first and foremost step for ME analysis is ME spotting which refers to detection of ME affected frames from a video. ME spotting is a highly challenging research problem and even human experts cannot correctly perform it because MEs are manifested using subtle face deformations and that too for a short duration. It is well established that changes in the human emotions, not only manifest ME but it also introduces changes in instantaneous heart rate. Thus, the manifestation of ME and changes in the instantaneous heart rate are related to the change in human expressions and both of them are estimated using temporal deformations of the face. This provides the motivation of this paper that aims to explore the feasibility of variations in the instantaneous heart rate for performing the correct the ME spotting. Experimental results conducted on a publicly available spontaneous ME spotting dataset, reveal that the variations in instantaneous heart rate can be utilized to improve the ME spotting.