DEV Community

#ocr

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why Converting Hindi PDFs to Word Produces Gibberish (Kruti Dev ASCII vs. UTF-8 Unicode)

Why Converting Hindi PDFs to Word Produces Gibberish (Kruti Dev ASCII vs. UTF-8 Unicode)

1
Comments
3 min read
How to turn scanned invoices and receipt photos into spreadsheet rows (no OCR setup)

How to turn scanned invoices and receipt photos into spreadsheet rows (no OCR setup)

Comments
4 min read
How to Make a Scanned PDF Searchable and Editable (Free OCR Guide)

How to Make a Scanned PDF Searchable and Editable (Free OCR Guide)

Comments
5 min read
AI Invoice Processing: OCR vs LLMs, Accuracy and Real Costs

AI Invoice Processing: OCR vs LLMs, Accuracy and Real Costs

Comments
8 min read
Textract vs Bedrock Data Automation vs Vision LLMs on Invoice Photos: 140 Images and a 6-Page Invoice, Real Calls

Textract vs Bedrock Data Automation vs Vision LLMs on Invoice Photos: 140 Images and a 6-Page Invoice, Real Calls

Comments
18 min read
yolowpdf: a PDF-to-Markdown parser written from scratch in Rust, plus its own OCR engine

yolowpdf: a PDF-to-Markdown parser written from scratch in Rust, plus its own OCR engine

Comments
3 min read
olmOCR-bench on Hugging Face: Three Rows Use a Different Average, and One Moves From 13th to 7th or 19th

olmOCR-bench on Hugging Face: Three Rows Use a Different Average, and One Moves From 13th to 7th or 19th

Comments
14 min read
Giving Claude and Cursor a Hebrew OCR tool over remote MCP

Giving Claude and Cursor a Hebrew OCR tool over remote MCP

Comments
5 min read
Pulling fields out of Hebrew invoices with a REST API

Pulling fields out of Hebrew invoices with a REST API

Comments
5 min read
Bank statement PDFs to CSV, part 7: installing tesseract on Windows, tested in CI

Bank statement PDFs to CSV, part 7: installing tesseract on Windows, tested in CI

Comments
3 min read
Bank statement PDFs to CSV, part 3: the scanned-PDF path — what OCR actually did, and what it didn't

Bank statement PDFs to CSV, part 3: the scanned-PDF path — what OCR actually did, and what it didn't

Comments
3 min read
Bank statement OCR gets the digits right and the layout wrong. Here is how to catch it.

Bank statement OCR gets the digits right and the layout wrong. Here is how to catch it.

Comments
5 min read
Da scansione a dati strutturati: pipeline OCR per documenti aziendali in Italia

Da scansione a dati strutturati: pipeline OCR per documenti aziendali in Italia

Comments
6 min read
I parse blood test PDFs on the phone, and the parser has no AI in it

I parse blood test PDFs on the phone, and the parser has no AI in it

1
Comments
5 min read
What sends a bill to review? Routing rules for Hindi + English OCR in a fleet ledger

What sends a bill to review? Routing rules for Hindi + English OCR in a fleet ledger

Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.
⌂ 换网址