Form OCR Digitizer — Automated Data Extraction
Akshay Kathiriya
Problem
Manual data entry from physical forms is slow, error-prone, and does not scale.
Solution
Built a Python pipeline using OpenCV for image preprocessing and OCR to extract structured fields from scanned forms, then store and verify records in MySQL.
Outcome
Automated extraction and verification workflow — reducing repetitive manual entry for form-heavy processes.
Stack
Python · OpenCV · MySQL
Note
Personal / student project — no client names. Demonstrates practical computer-vision and data-pipeline skills beyond LLM work.
Like this project
Posted Jun 14, 2026
Personal project: Python + OpenCV OCR pipeline that reads physical forms and stores structured data in MySQL. Automates manual data entry and verification.
