Modelpublic

Chanisorn/hand-gesture-robot-control

sourceHugging Faceupdated 2d agoView on Hugging Face

0likes

Model Card

Hand Gesture Robot Control Model

A RandomForestClassifier trained on MediaPipe hand-landmark vectors to recognize 9 hand gestures for live robot control (movement + claw).

Classes

forward, stop, backward, left, right, openclaw, closeclaw, default, none

Usage

python

import joblib
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="Chanisorn/hand-gesture-robot-control", filename="gesture_model.joblib")
scaler_path = hf_hub_download(repo_id="Chanisorn/hand-gesture-robot-control", filename="gesture_scaler.joblib")

clf = joblib.load(model_path)
scaler = joblib.load(scaler_path)

Input: a 63-length vector (21 MediaPipe hand landmarks x,y,z), normalized by translating to the wrist and scaling by the wrist-to-middle-finger-MCP distance. See gesture_config.py for the label list and robot command mapping.