Blog: M vs Microsoft: Episode 2

Go to the profile of ProjectM

Guess what emotions this person in the picture has:

😲 Surprise?

😔 Sad?

😐 Neutral?

😁 Happy?

😨 Fear?

😣 Disgust?

😒 Contempt?

😡 Anger?

What really happened to the person above: She doesn’t want to hug a new student who came to live with her family.

Let’s compare your answer with the results from two current emotion recognition technologies: M (the Artificial Intelligence platform developed by Ipmd) and Microsoft Azure.

Clearly, M’s analysis of human emotions has higher accuracy and complexity than Microsoft Azure’s.

It’s not easy to identify what exact feeling the person has on her face; however, emotion recognition technologies enable us to quantify one’s emotions. M, the AI platform developed by Ipmd, Inc., outcompeted other existing emotion recognition technologies, including Microsoft Azure, in terms of accuracy and complexity.

In this test, Microsoft Azure mistakenly identified 43.614% Happiness and 55.817% Neutral from the person. Microsoft Azure’s emotion recognition algorithm is based on analyzing one’s facial muscle movement. Simply detecting one’s facial muscle movement leads its inaccuracy. When the corner of the mouth moves slightly upward, as the person in the picture shows, Microsoft Azure is fooled by this muscle movement and categorizes it as “Happiness”. In many scenarios, people conceal their true feelings by showing different facial expressions. If emotion recognition technology were employed in identifying the mental status of people suffering from depression, falsely recognizing the patient’s sadness as happiness is dangerous.

M, instead, has a highly specialized artificial intelligence platform that accurately reads human emotions based on hidden micro-expressions. In this test, M identified 35.3% Disgust, 34.5% Sadness, 19.1% Contempt, and 7.8% Anger from the person. M successfully avoids the “trick” created by the person’s fake smile. Through analyzing micro-expressions, M was able to recognize some hidden emotions such as Anger and Contempt.

Interested? Here’s the official website of Ipmd, Inc.

Click to learn more about M.

Click to learn more about Microsoft Azure.

*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.

Source: Artificial Intelligence on Medium

Leave a Reply

Your email address will not be published. Required fields are marked *

Back To Top

Display your work in a bold & confident manner. Sometimes it’s easy for your creativity to stand out from the crowd.