emoCAPTCHA
This project is a CAPTCHA-like authentication system where the user is shown an emoji and must mimic the same facial expression in front of their camera to pass the verification.
Core trick
Scores a user's webcam frames against an emoji's target expression using MediaPipe face blendshapes, on-device or via OpenAI Vision.
Tags
Description
This project is a CAPTCHA-like authentication system where the user is shown an emoji and must mimic the same facial expression in front of their camera to pass the verification.
Regular CAPTCHAs are tedious. emoCAPTCHA makes verification playful by asking people to mimic emojis. Beyond fun, the goal is societal benefit: modern AI still struggles with reading human emotions, and ethically sourced examples of real facial expressions can help improve that. If users choose to contribute, their emoji-matching selfies could form a valuable dataset to train models to better understand human emotions.
README excerpt
## emoCAPTCHA This project is a CAPTCHA-like authentication system where the user is shown an emoji and must mimic the same facial expression in front of their camera to pass the verification. Built with Next.js 15, React 19, and Tailwind CSS. Scoring supports two engines: ### Name The “emo” in `emoCAPTCHA` stands for both “emotion” and “emoji”. - On-device (MediaPipe Tasks Vision) — private and fast, no network calls - Cloud (OpenAI Vision) — simple and robust; requires `OPENAI_API_KEY` ### Tech stack - Next.js (App Router, Turbopack) - React 19 - Tailwind CSS - MediaPipe Tasks Vision (on-device face blendshapes) - OpenAI Vision API (optional) ### Built with Cursor/Windsurf + GPT-5 This project was pair‑programmed in Cursor/Windsurf with GPT‑5 assistance. ### Project vision Regular CAPTCHAs are tedious. emoCAPTCHA makes verification playful by asking people to mimic emojis. Beyond fun, the goal is societal benefit: modern AI still struggles with reading human emotions, and ethically sourced examples of real facial expressions can help improve that. If users choose to contribute, their emoji-matching selfies could form a valuable dataset to train models to better understand human emotions. Ethics and privacy are central: any data contribution must be strictly opt‑in, consented, and protected with clear retention and anonymization policies. This repo ships with data collection disabled by default. ## Demo [![Watch the demo](https://i.ytimg.com/vi/IYQdEOPbSjE/maxresde