Digital OMR Reader

A Python-based Optical Mark Recognition (OMR) system designed to generate, scan, and grade custom OMR sheets. This project uses reportlab to generate print-ready OMR PDFs and OpenCV to process scanned images.

Features

• Custom OMR Sheet Generation: Create PDF OMR sheets with customizable layouts (Roll No, 5 Subjects, 20 Questions each).
• Synthetic Data Generation: Generate dummy filled OMR images for testing and validation without a physical scanner.
• OMR Scanning (In Progress): Scan and extract data from OMR sheets using Computer Vision.
• Data Export (In Progress): Export results to CSV for analysis.

Project Structure

Digital_OMR_Reader/
├── data/
│   └── sheets/             # Output directory for generated PDFs and images
├── src/
│   ├── demo_omr.py         # Generates the blank OMR PDF
│   ├── generate_test_image.py # Generates synthetic filled OMR images
│   └── omr_scanner.py      # (Planned) Core scanning logic
├── requirements.txt        # Python dependencies
└── README.md

Setup & Installation

1. Clone the repository:

   git clone https://github.com/yourusername/Digital_OMR_Reader.git
   cd Digital_OMR_Reader

2. Install dependencies:

   pip install reportlab opencv-python numpy

Usage

1. Generate Blank OMR Sheet

To create the printable PDF of the OMR sheet:

python src/demo_omr.py

Output: data/sheets/omr.pdf

2. Generate Synthetic Filled Data

To create a "fake" scanned image with random filled bubbles (useful for testing):

python src/generate_test_image.py

Output: data/sheets/test_filled_omr.jpg

3. Scan OMR Sheet (Coming Soon)

The scanner implementation is currently in development.

Technology Stack

• Python 3.x
• ReportLab: For PDF generation.
• OpenCV: For image processing and computer vision.
• NumPy: For array manipulations.

License

MIT License