A Flask-powered web application that extracts text from images using Tesseract OCR. The app supports image preprocessing for improved accuracy, an intuitive interface, and the ability to download extracted text.

• OCR-Based Text Extraction: Leverages Tesseract OCR for reliable text recognition.
• Preprocessing for Accuracy: Automatically preprocesses images (grayscale and thresholding).
• Image Preview: See your uploaded image before processing.
• Text Export: Download extracted text as a .txt file with a single click.
• Responsive UI: A mobile-friendly, modern interface.

You can view a live demo of the app here

• Backend: Flask, Python
• Frontend: HTML, CSS, JavaScript
• Image Processing: OpenCV, Pillow (PIL)
• OCR: Tesseract OCR

1. Python 3.7+
2. Tesseract OCR:
   • Windows: Download Tesseract.
   • Linux/Mac:

     sudo apt install tesseract-ocr

1. Clone the repository:

   git clone https://github.com/HariPasapuleti/Text-Extractor.git cd Text-Extractor

2. Install dependencies:

   pip install -r requirements.txt

3. Configure Tesseract path:

   • Windows:

     pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

   • Linux/Mac: No changes needed (default path).

4. Start the Flask server:

   python text_extractor.py

1. Upload an Image: Accepts .jpg or .png formats.
2. Preview: Check the image preview before processing.
3. Extract Text: View extracted text directly on the page.
4. Download: Save the extracted text as a .txt file.