SmartOrderReader

SmartOrderReader is a smart Python tool that automatically processes images of invoices, order confirmations, or receipts. It uses OCR (Optical Character Recognition) to extract the Order Number and Order/Creation Date from each image with high accuracy. The program then organizes the extracted data into a clean table and saves it as a CSV file for easy management and use in Excel or Google Sheets.

Features

• ✅ Extract Order Number/Invoice Number/Order ID from images
• ✅ Extract Order Date/Invoice Date/Creation Date from images
• ✅ Support for multiple image formats (JPG, PNG, BMP, TIFF)
• ✅ Process multiple images in a single run
• ✅ Support for both English and Urdu text
• ✅ Clean table output with professional formatting
• ✅ CSV export for easy Excel/Google Sheets integration
• ✅ Automatic image preprocessing for better OCR accuracy
• ✅ Handles various date formats (MM/DD/YYYY, YYYY-MM-DD, Month DD, YYYY)
• ✅ Smart pattern matching for different invoice formats

Prerequisites

• Python 3.7 or higher
• Tesseract OCR engine

Installing Tesseract OCR

Ubuntu/Debian:

sudo apt-get update
sudo apt-get install tesseract-ocr
# For Urdu support (optional):
sudo apt-get install tesseract-ocr-urd

macOS:

brew install tesseract
# For Urdu support (optional):
brew install tesseract-lang

Windows:

• Download and install from: https://github.com/UB-Mannheim/tesseract/wiki
• Add Tesseract to your system PATH

Installation

1. Clone the repository:

git clone https://github.com/Next-GenDeveloper/SmartOrderReader.git
cd SmartOrderReader

2. Install Python dependencies:

pip install -r requirements.txt

Usage

Basic Usage

Process one or more images:

python order_reader.py invoice1.jpg invoice2.png receipt.jpg

Advanced Usage

Specify custom output file:

python order_reader.py *.jpg --output my_orders.csv

Process images with Urdu text support:

python order_reader.py invoice.png --lang eng+urd

Process all images in current directory:

python order_reader.py *.jpg *.png

Command-Line Options

usage: order_reader.py [-h] [-o OUTPUT] [-l LANG] images [images ...]

SmartOrderReader - Extract order data from invoice/order images

positional arguments:
  images                Image files to process (supports jpg, png, jpeg, bmp, tiff)

options:
  -h, --help            show this help message and exit
  -o OUTPUT, --output OUTPUT
                        Output CSV filename (default: order_data.csv)
  -l LANG, --lang LANG  OCR language (default: eng, use eng+urd for English+Urdu)

Output Format

The tool provides two types of output:

1. Table Format (Console)

================================================================================
EXTRACTED ORDER DATA
================================================================================

+-------------------+----------------+------------------+
| Image File Name   | Order Number   | Order Date       |
+===================+================+==================+
| invoice1.jpg      | ABC12345       | 12/25/2023       |
+-------------------+----------------+------------------+
| invoice2.png      | INV-2024-001   | January 15, 2024 |
+-------------------+----------------+------------------+

2. CSV Format

Image File Name,Order Number,Order Date
invoice1.jpg,ABC12345,12/25/2023
invoice2.png,INV-2024-001,January 15, 2024

The CSV file is automatically saved and can be directly imported into Excel or Google Sheets.

Supported Patterns

Order Number Patterns

• Order #, Order No., Order Number
• Invoice #, Invoice No., Invoice Number
• Order ID
• PO # (Purchase Order)
• Reference #, Ref #

Date Patterns

• Order Date, Invoice Date
• Date, Issue Date
• Created On, Transaction Date
• Creation Date

Date Formats

• MM/DD/YYYY or DD/MM/YYYY (e.g., 12/25/2023)
• YYYY-MM-DD (e.g., 2023-12-25)
• Month DD, YYYY (e.g., December 25, 2023)

How It Works

1. Image Preprocessing: Images are converted to grayscale and optimized for better OCR accuracy
2. OCR Text Extraction: Tesseract OCR extracts all text from the image
3. Pattern Matching: Smart regex patterns identify order numbers and dates
4. Data Extraction: Most relevant information is extracted based on priority
5. Output Generation: Results are formatted as table and CSV

Troubleshooting

"pytesseract.TesseractNotFoundError"

• Make sure Tesseract OCR is installed and in your system PATH
• On Windows, you may need to set the path manually in the script

No text extracted from image

• Ensure the image is clear and readable
• Try increasing image resolution
• Check if the text is in a supported language

Wrong data extracted

• Make sure the image quality is good
• Verify that order number/date labels are clearly visible
• Try different image preprocessing settings

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Author

Created by Next-GenDeveloper

Acknowledgments

• Tesseract OCR for text recognition
• OpenCV for image preprocessing
• Python community for excellent libraries