# Ml5js posenet single mode still return multiple face key points

**URL:** https://discourse.processing.org/t/ml5js-posenet-single-mode-still-return-multiple-face-key-points/23636
**Category:** Libraries
**Created:** [September 2, 2020, 3:00pm UTC](https://discourse.processing.org/t/ml5js-posenet-single-mode-still-return-multiple-face-key-points/23636 "2020-09-02T15:00:21Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![stephanschulz](https://avatars.discourse-cdn.com/v4/letter/s/d9b06d/32.png) [@stephanschulz](https://discourse.processing.org/u/stephanschulz)
#### Post date: [September 2, 2020, 3:00pm UTC](https://discourse.processing.org/t/ml5js-posenet-single-mode-still-return-multiple-face-key-points/23636/1 "2020-09-02T15:00:21Z")

</div>

I have set` detectionType: 'single'` and feed my video in this way `poseNet.singlePose(video);`  
It’s true that only one skeleton get’s detected but when 2 people are present body parts key-points get scattered between these people.  
Also if one person wears a face mask only their eye get detected and the 2nd person gets mouth and ear key-points.

I know I can work around it by filtering and measuring key-point distances. But maybe there is already a build in function to keep key-points in a reasonable distance to each other.

[https://ml5js.org/reference/api-PoseNet/](https://ml5js.org/reference/api-PoseNet/)