https://selvamsubbiah.com/tags/face-landmark-detection/Recent content in Face-Landmark-Detection on Selvam SubbiahHugo -- 0.154.3en-usSun, 21 Nov 2021 00:00:00 +0000https://selvamsubbiah.com/mediapipe-facemesh-triangles-in-tensorflow-js-part-2/Sun, 21 Nov 2021 00:00:00 +0000https://selvamsubbiah.com/mediapipe-facemesh-triangles-in-tensorflow-js-part-2/<p>This article is the continuation of the <a href="https://selvamsubbiah.com/mediapipe-facemesh-in-tensorflow-js/">previous article</a> on MediaPipe Face Mesh model in TensorFlow.js, where we looked at the basic usage of this model. Here, we will look at how to connect the 468 3D facial landmark predictions as multiple triangles to create a <a href="https://en.wikipedia.org/wiki/Triangle_mesh" target="_blank" rel="noopener noreferrer">triangle mesh</a> of the face.</p> <h2 id="1-triangle-mesh">1. Triangle Mesh</h2> <p>To create a triangle mesh from the 468 [x,y,z] coordinates, we will need to identify which are the set of points that need to be connected to form triangles. Luckily Google has provided those indexes for us to draw the triangle mesh. It is present in the <a href="https://github.com/tensorflow/tfjs-models/blob/master/face-landmarks-detection/demo/triangulation.js" target="_blank" rel="noopener noreferrer">triangulation.js</a> file located in the Github repo of the pre-trained model.</p>