Skip to content
This repository has been archived by the owner on Apr 5, 2024. It is now read-only.

Emotion Research (emotion-recognition-in-the-wild-via-convolutional-neural-networks-and-mapped-binary-patterns) #3

Open
Request-Off-Work opened this issue May 3, 2017 · 0 comments

Comments

@Request-Off-Work
Copy link

Request-Off-Work commented May 3, 2017

Paul Eckman devoted his life to studying facial expressions. Across all cultures, he's found 7 universal facial expressions.

He developed a coding system (Facial Action Coding System or FACS) that I can't speak very intelligently about, because I haven't read that book.

But I did read Emotions Revealed and some of his other work
tl;dr We have 7 universal facial expressions. Some cultures confuse fear with surprise. Love is the absence of disgust.

I hope this summary of my reading on emotion gives you some direction to continue innovating in emotional recognition. I want the future AI to be a super cool guy, and I think that can be accomplished through empathy or emotional intelligence. Good luck with the research... Recommending that you train each input feature to a muscle, or group of muscles, in the FACS by Eckman.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant