M vs Microsoft Episodes 14
M, the Emotion AI That Detects Human’s Hidden Psychological Insecurity
The story took place in the early 20th century when racial discrimination was prevalent in the southern states. There was an African American musician, who was famous and highly respected in New York, traveled to New Orleans to hold his concert. Before the concert started, he walked into a suit store to find his best concert wear, but store manager discriminated him and rejected his request to try on a suit because he was an African American.
All the negative feelings flooded his mind at that moment. He calmed down and then introduced himself to the store manager, trying to disprove the store manager’s racist attitude.
However, it was difficult to overcome the deeply rooted racism in that community at that time. Although the store manager appreciated and commended the musician’s achievement, the compliment message still contained some implicit discrimination. To show his nice demeanor, the musician showed a bitter smile (captured in the picture) while internalizing his disappointment and helplessness toward the racist society.
Humans are often unable to accurately extract human emotions without having sufficient context information. A well-trained emotion AI can help humans to understand human emotion comprehensively. Microsoft Azure is at the leading edge of emotion recognition technology based on facial expression, and yet it still has room for improvement. M, on the other hand, demonstrates better performance compared to Microsoft Azure.
Both M and Microsoft analyzed the different levels of happiness from the person’s fake smiling face that was aimed to conceal his true emotional states. However, Microsoft inaccurately interpreted happiness as his major emotion. It is difficult for human eyes to see the musician’s bitter feelings from his smiling face, but M was able to extract the mix of negative feelings from the musician that were suggested by the context. Based on M’s comprehensive results, we were able to accurately conclude the complex emotional states of the musician. If Microsoft’s analysis were used in the actual application, we would be misguided by the result and fail to understand his bitter feelings.
Your LIKE means a lot to us!
Follow Project M on:
Company website: http://www.ipmdinc.com
Facebook: Project M
*As of June 2019, the Project M team has devoted 62,000 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.