OCR AI Shell 🖥️🤖

Welcome to the OCR AI Shell repository! This project is an AI-powered Optical Character Recognition (OCR) tool that allows you to recognize text from images and webcams. With features like offline summarization and a user-friendly GUI, this tool makes text extraction straightforward and efficient.

Table of Contents

1. Features
2. Installation
3. Usage
4. Technologies Used
5. Contributing
6. License
7. Support

Features ✨

• AI-Powered OCR: Leverage advanced AI algorithms for accurate text recognition from images and webcam feeds.
• Offline Summarization: Summarize text efficiently without needing an internet connection.
• User-Friendly GUI: Built with Tkinter, the graphical interface is intuitive and easy to navigate.
• Multiple Formats: Supports various image formats for text extraction.
• Real-Time Processing: Capture and recognize text in real-time using your webcam.
• Cross-Platform: Works on Windows, macOS, and Linux.

Installation ⚙️

To get started, you need to download the latest release of the OCR AI Shell. Visit the Releases section to download the necessary files.

Once downloaded, follow these steps:

1. Extract the Files: Unzip the downloaded file.
2. Install Dependencies: Open your terminal or command prompt and run:

   pip install -r requirements.txt

3. Run the Application: Execute the main script with:

   python main.py

Usage 📖

After installation, you can start using the OCR AI Shell:

1. Launch the Application: Open the application from your desktop or terminal.
2. Select Input Source: Choose whether to use a webcam or upload an image.
3. Capture or Upload: If using a webcam, click on the "Capture" button. If uploading an image, select the file from your system.
4. Extract Text: Click on the "Extract" button to process the image. The recognized text will appear in the text area.
5. Summarize Text: If you wish to summarize the extracted text, click on the "Summarize" button.

Technologies Used 🔧

The OCR AI Shell is built using several technologies:

• Python: The core programming language.
• Tkinter: For the graphical user interface.
• Pytesseract: For OCR capabilities.
• OpenCV: For image processing.
• Gemma3 and LLava: For advanced AI features.
• Ollama: For offline summarization.

Contributing 🤝

We welcome contributions! If you want to help improve the OCR AI Shell, follow these steps:

1. Fork the Repository: Click the "Fork" button at the top right of this page.
2. Clone Your Fork: Run the following command in your terminal:

   git clone https://github.com/YOUR_USERNAME/ocr-ai-shell.git

3. Create a Branch: Create a new branch for your feature or bug fix:

   git checkout -b feature-name

4. Make Changes: Implement your changes and commit them:

   git commit -m "Description of changes"

5. Push to Your Fork: Push your changes to GitHub:

   git push origin feature-name

6. Create a Pull Request: Go to the original repository and click on "New Pull Request".

License 📜

This project is licensed under the MIT License. See the LICENSE file for more details.

Support 💬

If you encounter any issues or have questions, feel free to open an issue on GitHub. You can also check the Releases section for updates and new features.

Thank you for using OCR AI Shell! Your feedback is invaluable in helping us improve this tool. Happy text extracting!