Human Error Identification

In the latest issue of IEEE Intelligent Systems:   Automatically analyzing Facial-Feature Movement to Identify  Human Errors,  by Maria Jabon, Sun Jao Ahn and Jeremy Bailenson of Stanford University.      Using facial feature points  automatically extracted from short video segments researchers couple computer vision with machine learning to predict performance over an entire task and at any given instant  within the task.  We spent some time look at  the ability to look at shoppers while they were interacting with product on shelf to see their interest and likelihood of buying,   The full article is not free online  at this time.