Can AI Detect Combinations of Hidden Emotions of Fear, Anger and Sadness?
What happened to the person in this picture?
She identified a much stronger and fierce competitor right before the competition starts. At this moment, she felt the fear from her inner self because she understood that she would be no match for the superior competitor. After imagining herself in different losing situations, she became more afraid to lose the competition. When people were in this fight-or-flight situation, many of them would choose to flight. However, in this scenario, taking the fight response was the only option. In order to compete with the strong competitor, she had to drive more energy from her anger and rage to strengthen herself in order to fight against her inner fear. Driven by these complex emotions, she unconsciously revealed her anger on her face.
Let’s take a look at M’s and Microsoft’s performance in analyzing this person’s emotion at that moment:
M, the AI developed by the Project M team, successfully and accurately identified the three key emotions: Fear, Anger and Sadness. M read “Fear” (40.1%) as the primary emotion and “Anger” (30.4%) as the secondary emotions and “Sad” (16.4%) as the tertiary emotion from the person’s face, correctly matched the person’s current emotional states.
Microsoft, however, read 99% “Neutral” and failed to read the person’s negative and vulnerable emotional states. To make emotional AI useful in field applications, the ability to read these emotions is essential.
Your LIKE means a lot to us! Follow Project M on:
Project M: https://projectm.ipmdinc.com
IPMD website: http://www.ipmdinc.com
Medium: Project M
Facebook: Project M
Blogger: Project M
LinkedIn: Project M
*As of April 2019, the Project M team has devoted 58,000 hours to the AI platform, M. The sample input data we are using is the pure testing data that is completely new to M and Microsoft (assumed) and is never been used to train M, so this comparison is a fair trial between M and Microsoft. We appreciate Microsoft, the leader of the industry and emotional AI sector, for allowing the general public to test their testing site for identifying human emotions based on facial expressions.