Skip to content

Latest commit

 

History

History
32 lines (25 loc) · 1.07 KB

README.md

File metadata and controls

32 lines (25 loc) · 1.07 KB

PDF Extraction using Tesseract

  • About

An OCR project as a Proof of Concept to deploy a machine learning project using Streamlit. The text extraction process is accompanied with image processing for better text recognition and achieving higher efficiency.

  • Libraries / Frameworks

    1. Streamlit - UI
    2. Tkinter - File download setup
    3. Pytesseract
    4. Pdf2Image
    5. OpenCV - Image Processing

  • Code Execution

    1. Make sure you have Python 3.8 installed on the system.
    2. Open cmd where the contents are unzipped.
    3. Run the below command to install required packages.

      pip install -r requirements.txt

    4. Install Tesseract setup file
    5. Once all packages are installed, run the following command:

      streamlit run OCR.py

If facing any issues, contact me

  • Output

Bounding Box around recognized text output1

Text extraction and document saved output2

Extracted Text Output output3