Hand Finger Counter

A real-time AI-powered hand finger counter using Python, OpenCV, and MediaPipe. This project detects hands through a webcam and counts the number of fingers held up in real-time.

Features

• Real-time Detection: High-speed hand tracking using MediaPipe.
• Dual Hand Support: Counts fingers from both hands simultaneously.
• Robust Logic:
  • Uses distance-based logic for Thumb detection.
  • Uses Y-coordinate comparison for the other four fingers.
• Sleek UI: Displays the total count in a styled overlay on the video feed.

Visuals

The application displays a live feed with:

1. Hand landmarks and skeletal connections.
2. An overlay box showing the total count of fingers currently visible.

Installation

Prerequisites

• Python 3.8+
• Webcam

Setup

1. Clone the repository:

   git clone https://github.com/Tusm11/Finger-Counter.git

2. Install dependencies:

   pip install opencv-python mediapipe

3. Run the application:

   python main.py

Controls

• Press any key: Closes the application.

How it Works

1. Hand Tracking: MediaPipe identifies 21 key landmarks for each hand.
2. Thumb Detection: Calculates the Euclidean distance between the thumb tip and the index base. If the distance exceeds a threshold, the thumb is considered "open".
3. Finger Detection: Compares the Y-coordinate of each finger's tip with its middle joint. If the tip is higher (lower Y-value in image coordinates), the finger is considered "open".
4. Summation: Adds up all "open" fingers across all detected hands.