ml5js/ml5-library

Add useful keypoint getters for Facemesh

Open

#1,028 建立於 2020年7月12日

在 GitHub 查看
 (11 留言) (0 反應) (0 負責人)JavaScript (6,136 star) (905 fork)batch import
facemeshfeature requestgood first issue

描述

See the keypoint map: https://github.com/tensorflow/tfjs-models/blob/master/facemesh/mesh_map.jpg

In the ml5.js Facemesh model, we can consider providing some functions that return an array of keypoints for useful facial landmark ranges like the left eye, right eye, mouth, etc. For example:

facemeshInstance.getLeftEye() // returns [<keypoint 22>, <keypoint 23>, <keypoint 24>, ...]

貢獻者指南

技術棧
javascript
領域
machine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-3 hours
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
ml5 library fundamentalsFacemesh keypoint mapJavaScript array methods
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
65
研究方向
Start by examining the Facemesh model implementation in the ml5 library, particularly the keypoint array from the TensorFlow.js Facemesh model. Look at the referenced keypoint map (mesh map.jpg) to understand the indices for facial features. Then create new methods like getLeftEye() that filter the keypoints by predefined index ranges. Check the existing codebase for similar patterns (e.g., other getter methods) to follow the same style.