From raw document to structured data
SanadGah converts Persian printed documents — through a multi-stage processing pipeline — into searchable text, key fields, and structured JSON output, via API and in batch.
Document intake
Submitting documents via REST API, individually or in batch. PDF and image support.
Image preprocessing
Rotation correction, contrast enhancement, and noise removal — to improve input quality before OCR.
Specialized Persian OCR
Text extraction from Persian printed documents using a specialized Persian OCR engine, designed for connected letters and contextual Persian letterforms.
Linguistic post-processing
Correcting OCR output with natural language processing (NLP) — reducing errors in Persian words, Persian numerals, and punctuation.
Field extraction
Identifying key fields from contracts and invoices (parties, date, amount, document number) — initial version, extensible.
Structured output
Delivering results as JSON and full text via API and webhooks — ready to connect to enterprise systems.
What you receive
- Full document text, searchable
- Extracted key fields (contracts, invoices)
- Structured JSON output + completion notification via webhook