# Face Emotions Classification

### Competition Description
At ABI we're always concerned about the customer experience and trying to understand their behavior to provide the best beverages in the market.  However, only words do not match emotions and what a person is actually feeling.

What if we create Machine Learning models to understand patterns in images and say if a customer is happy or not while it's drinking one of our beverages?

That's the goal of this challenge!! We are providing a dataset of 35K images of people in many situations and their feelings. **Are you able to create a model to understand what's their face is telling you?**

Good Luck 🍀

---
### Participant Eligibility
**To be eligible, you MUST be an ABI employee and have a valid corporate email address**


---
### Prize
One Winner - $100 (USD) Visa e-Gift Card 

---
### Practice Skills
-   Computer vision fundamentals including simple neural networks
-   Classification methods such as SVM and K-nearest neighbors

---
### Hosts

**Analytics Academy**
[Tina Gui](mailto:tina.gui@ab-inbev.com?subject=[Kaggle%20Competition])
[Bruno Raposo](mailto:bruno.raposo@ab-inbev.com?subject=[Kaggle%20Competition])
[Gopakumar R](mailto:gopakumar.r@ab-inbev.com?subject=[Kaggle%20Competition])


**AmbevTech**
[Hugo Zanini](mailto:hugozanini@ambev.com.br?subject=[Kaggle%20Competition])



---
### Acknowledgements
The images were gathered from many datasets and it's a mix of the following works:
- [The Extended Yale Face Database B](http://vision.ucsd.edu/~iskwak/ExtYaleDatabase/ExtYaleB.html)
- [Labeled Faces In The Wild](http://vis-www.cs.umass.edu/lfw/)
- [The Japanese Female Facial Expression (JAFFE) Database](https://zenodo.org/record/3451524#.YHeSy-hKhPY)
- [Indian Movie Face database (IMFDB)](http://cvit.iiit.ac.in/projects/IMFDB/)


---
### References
[0] https://www.verywellmind.com/understanding-emotions-through-facial-expressions-3024851

[1] Cover image: https://www.stocksy.com/463065/selfie-friends-in-pub