Skip to content

Created a webcam stream using react app. Transfer learning is used to import facemesh which is a pre-trained deep learning library to detect the face from tensorflow.js and by using javascript canvas drew all the keypoints and triangles on the app.

Notifications You must be signed in to change notification settings

Anuhya101/Realtime_FaceLandmark_Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Realtime_FaceLandmark_Detection

Created a webcam stream using react app. Transfer learning is used to import facemesh which is a pre-trained deep learning library to detect the face from tensorflow.js and by using javascript canvas drew all the keypoints and traingles on the app.

What is facial landmark detection

Machine learning technique that detects different points on your face. When you combine these together you're able to generate a mesh. The model in this video detects 486 3D facial landmarks to infer the approximate surface geometry of a human face. This model is used in snapchat filters and there's so much more that it can be used for like emotion analysis and face tracking.

Untitled.mp4

The model can also detect multiple faces at a time

Resources

Tensorflow.Js models: https://www.tensorflow.org/js/models

HTML Canvas: https://developer.mozilla.org/en-US/d...

Create React App: https://reactjs.org/docs/create-a-new...

About

Created a webcam stream using react app. Transfer learning is used to import facemesh which is a pre-trained deep learning library to detect the face from tensorflow.js and by using javascript canvas drew all the keypoints and triangles on the app.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published