Filters Using Facial Key Points Detection

1) Define your scope or domain where the use case is relevant or prevalent

This can be used as a building block in several applications, such as:

• tracking faces in images and video

• analyzing facial expressions

• detecting dysmorphic facial signs for medical diagnosis

• biometrics/face recognition

2) What is your main story?

We are using kaggle competition dataset to detect keypoints on human faces which can be used for other applications like: Face tracking, improving facial recognition, gender distinction, virtual makeover, face replacement, facial expressions detection. As there are rumors of TikTok going to get banned in upcoming days, we see that there are lot of users there from TikTok that will look for replacement and will look for the one with best filters available.

3) Who are the characters or people in the main story?

There are sample images of different people provided by Dr. Yoshua Bengio of the University of Montreal. Which contains images of faces of people in different angles and we have 15 points on the face. There are three points for each eye, two for each eyebrow, one for tip of the nose and 4 for lips. After that we have used our team images for testing and detecting facial points

4) What problem happened to them?

Due to the ongoing pandemic people are not allowed to go out for having fun and lot of them are going to social media platforms to make videos and take photos that will have filters on them where they can relax their mind and also have fun.

5) Where did the problem take place?

Problem is taking place everywhere in the world as the pandemic has started you can see many new applications are there in the market which help people to make videos and take photos with filter on, like Snapchat and Instagram.

6) Why?

As per latest news, TikTok is getting banned in USA which is most common for adding filters in videos. Also to add filter based on user face using keypoints,

7) How?

If you would like, you can add a dimension of how. How did it happen? Sometimes, the answer to how can be covered by what, when and where.

8) What new aspect your team is adding to the Kaggle challenge (Please be very specific and clearly explain what you are trying to add to the Kaggle Challenge)

We will be adding a filter using the facial keypoint that we got through our model.