Back to feed
Dev.to
Dev.to
7/27/2026
Make any scan searchable - locally, no Python, no Ghostscript, no upload

Make any scan searchable - locally, no Python, no Ghostscript, no upload

Short summary

DeepOCR is a single static Rust binary that adds searchable text layers to scanned PDFs entirely offline — no Python, Tesseract, Ghostscript, or cloud upload required. The OCR engine (ocrs, pure Rust) and its recognition model ship inside the binary, making it suitable for air-gapped environments and sensitive documents like contracts, IDs, and medical records. v0.1 supports Latin script only, with CJK and PDF/A on the roadmap.

  • •Single static Rust binary with embedded OCR model — runs fully offline, no dependencies
  • •Outputs searchable PDFs with invisible text layers; original files are never modified
  • •v0.1 limited to Latin script; CJK, additional languages, and PDF/A planned for future releases

Generated with AI, which can make mistakes.

#ai-tools#open-source
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

TrulyFreeOCR – a Java OCR pipeline in a single fat JAR, zero native deps required
Dev.to
Parsing documents for air-gapped RAG: no cloud, no JVM, no Python
Dev.to
Arabic OCR with an API: Make Scanned Arabic PDFs Searchable (Python)
Dev.to
Unlimited-OCR: Parsing a 40-Page PDF in One Pass Without Your GPU Melting
Dev.to