Hacker News Reader

Thanks for sharing!

Since OCR is a somewhat slow process, how does the WASM approach compare to running libtesseract in a subprocess and use some IPC layer to talk to Go? It would require a separate C++ compiler, but not CGo.

> one of the largest Open Source OCR

Tangential, but are there others as large as Tesseract? It seems to pop up anywhere I look.

View on HN

> Tangential, but are there others as large as Tesseract?

The one serious competition is PaddleOCR, which is faster on GPU, and also works better for Chinese and other non-Western scripts.

There are some newer ML-based projects like DocTR that have been catching up, at least for some use cases.

My intentions was a "pure Go" approach, but that is probably more performant.

I imagine just calling the Tesseract CLI from Go would be simplest if that's all you wanted.

Reply on news.ycombinator.com