handpose-facemesh-demos
🎥🤟 8 minimalistic templates for tfjs mediapipe handpose and facemesh
A openCV program that detects faces and displays Tiktok cats.
git clone https://github.com/reinesana/MeowCV.gitreinesana/MeowCVAn openCV + mediapipe program that detects facial expressions and displays goated Tiktok cats like Rigby and Larry
MeowCV is a CV program that maps human facial expressions to popular cat reactions on Tiktok in real time.
Using your webcam and the mediapipe library, the system tracks key facial landmarks and displays a corresponding cat image when it detects expressions. Each cat is triggered using lightweight rules based on landmark movement like:
Note: This program is designed to be fun and easy to extend — perfect for experimenting with facial heuristics and expression detection.
git clone https://github.com/reinesana/MeowCV.git
Python 3.9 – 3.12 required (tested on Python 3.11.7). Python 3.13+ is not supported for mediapipe==0.10.14.
pip install -r requirements.txt
python main.py
You can customize how the system behaves by editing the configuration values in main.py.
Measures the vertical distance between the upper and lower eyelids for both eyes and triggers the shocked cat.
eye_opening_threshold = 0.026 # very exaggerated shock eye_opening_threshold = 0.020 # subtle eye widening
Measures the vertical distance between the upper and lower lips and triggers only when the mouth opens in a narrow “tongue-out” shape.
mouth_open_threshold = 0.045 # tongue must be very visible mouth_open_threshold = 0.030 # easier tongue trigger
Measures how close the upper and lower eyelids are and controls when the side-eye cat is triggered.
squinting_threshold = 0.016 # very strict glare squinting_threshold = 0.020 # softer glare
Have fun 🐱💻
MIT License © 2026 Shana Nursoo
more like this
🎥🤟 8 minimalistic templates for tfjs mediapipe handpose and facemesh
meine 🌒 - A CLI file manager and system utility built with Textual. It combines intuitive command parsing with rich t…
search projects, people, and tags