Initial release of OCRApp.
OCRApp is a config-driven OCR pipeline that extracts structured data from images using template-based extraction and stores results in a database.
Features:
- Template-based OCR extraction
- Bounding box, regex, and label-nearby extractors
- Image preprocessing for improved OCR accuracy
- SQLite database storage
- Configurable templates
- Desktop UI for managing templates and running OCR
Requirements:
Tesseract OCR must be installed:
https://github.com/UB-Mannheim/tesseract/wiki
Run:
Extract the zip and launch ocrapp.exe.