/optical-character-recognition

This is a Streamlit web app leveraging EasyOCR to extract text from uploaded images, presenting it with confidence scores and visual annotations, simplifying Optical Character Recognition tasks.

Primary LanguageJupyter Notebook

ScanMaster OCR

ScanMaster OCR is a simple Streamlit web application that allows users to upload images (in PNG, JPG, or JPEG format) containing text and performs Optical Character Recognition (OCR) to extract and display the text content. It utilizes the EasyOCR library for text extraction and provides a user-friendly interface for viewing the extracted text along with prediction confidence scores.

Features:

  • Supports text extraction from uploaded images in PNG, JPG, or JPEG format.
  • Utilizes EasyOCR library for accurate and efficient Optical Character Recognition (OCR).
  • Displays extracted text along with prediction confidence scores in tabular format.
  • Provides visual annotations on the uploaded image with bounding boxes around detected text.

Usage:

  • Clone the repository to your local machine.
  • Install the required dependencies using pip install -r requirements.txt.
  • Run the Streamlit app locally using streamlit run app.py.
  • Upload an image containing text to perform OCR.
  • View the extracted text along with prediction confidence scores in the table.
  • Visualize the uploaded image with annotated bounding boxes around detected text.

Requirements:

  • Python 3.6 or later
  • EasyOCR
  • Streamlit
  • OpenCV
  • NumPy
  • Pandas
  • PIL (Python Imaging Library)
  • Base64

Contributing:

Contributions are welcome! If you encounter any issues or have suggestions for improvements, feel free to open an issue or submit a pull request.

Live Demo

Recording.mp4