OCR Extractor

A simple and efficient OCR-based data extraction tool for Indian PAN and Aadhaar cards using Tesseract OCR.

🆕 What's New in v0.1.3

• Corrected example usage in README:
  • print(pan_data.get_pan())
  • print(aadhaar_data.get_aadhaar())
• Includes all features from v0.1.2:
  • Added tesseract_cmd parameter to ExtractAadhaarData and ExtractPanData for custom Tesseract paths.
  • Fixed issue with preprocessing argument (preprocess) in child classes not being passed correctly.

(For full version history, see CHANGELOG.md)

✨ Features

• Extract PAN card data with a single function call
• Extract Aadhaar card data with a single function call
• Built-in preprocessing option for better OCR accuracy
• Cross-platform support (Windows, Linux, macOS) with configurable Tesseract path

📦 Installation

pip install ocr-pro

🚀 Usage

Extract PAN Card Data

from ocr import ExtractPanData

# Default usage (preprocess=False by default)
pan_data = ExtractPanData("pan_image.jpg", tesseract_cmd="/usr/bin/tesseract")

print(pan_data.get_pan())

Extract Aadhaar Card Data

from ocr import ExtractAadhaarData

# You can also enable preprocessing
aadhaar_data = ExtractAadhaarData("aadhaar_image.jpg", tesseract_cmd="/usr/bin/tesseract", preprocess=True)

print(aadhaar_data.get_aadhaar())

Arguments

• filepath (str) → Path to the image file
• tesseract_cmd (str, optional) → Path to the Tesseract executable (default: system auto-detection or "C:\Program Files\Tesseract-OCR\tesseract.exe" on Windows)
• preprocess (bool, default=False) → Whether to apply preprocessing for better OCR results

⚙️ Requirements

• Python 3.7+
• Tesseract OCR installed on your system

📜 License

MIT License