Metal OCR Chassis Detector

An AI-powered metal OCR detector that extracts chassis/serial numbers from images where the numbers are punched on metal surfaces.
Built with Streamlit and Google Gemini AI, this tool helps in automating inspection processes for manufacturers, mechanics, and dealerships.

---

🚀 Features

• 📷 Upload or capture an image of a metal chassis number.
• 🔍 Uses Gemini AI for precise OCR with lookalike character distinction (0≠O, 1≠I, etc.).
• 🎨 Beautiful Streamlit UI with a modern theme.
• ⚡ Real-time chassis number detection.

---

🛠️ Tech Stack

• Python 3.10+
• Streamlit
• LangChain
• Google Gemini AI
• dotenv

---

⚙️ Installation & Setup

1️⃣ Clone the repository

git clone https://github.com/Arsalan692/Metal-OCR-Chassis-Detector
cd Metal-OCR-Chassis-Detector

2️⃣ Create a virtual environment (optional but recommended)

python -m venv venv
source venv/bin/activate   # For Linux/Mac
venv\Scripts\activate      # For Windows

3️⃣ Install dependencies

pip install -r requirements.txt

4️⃣ Set up API key

🔑 Setting Up Google Gemini API Key

• Go to Google AI Studio: https://aistudio.google.com
• Sign in with your Google Account.
• Click Get API Key from the sidebar.
• Create a new API key and copy it.

5️⃣ Add API Key

Create a .env file in the project root and add your keys:

# GOOGLE API KEY
GOOGLE_API_KEY=your_api_key_here

6️⃣ Run the app

streamlit run Metal_OCR_detection.py

---

📸 Demo Screenshots