[Icko]

Last I compared them, (1-2 years ago), Google OCR was much much better and supported more languages than tesseract. There was also an OCR in openCV, which was slightly better than tesseract, but not good enough to be useful.

[rafram]

I’m not aware of any separate OCR in OpenCV. Some builds include an interface to Tesseract, which might be what you’re thinking of. Tesseract certainly benefits from preprocessing (conversion to grayscale, posterization) with OpenCV.

[Icko]

There was "EAST OCR" detector, which is basically someone put a deep learning model in openCV somehow. https://www.folio3.ai/blog/text-detection-by-using-opencv-an...

[lasagna_coder]

What are these projects are you referring to? AFAIK Tesseract is sponsored by Google, from what I understand it is state of the art, ie it is Google OCR. Searching for OCR with OpenCV only reveals using OpenCV with Tesseract, not rolling its own OCR, OpenCV being used to preprocess images to optimise them for Tesseract. Maybe I'm missing something, so I'm interested if you can point me in the right direction.

[spi]

Google OCR is definitely not the same as Tesseract, although it's true that Tesseract is maintained by Google. Google OCR has definitely much higher accuracy and is significantly faster (basically always taking 1s for inference, while Tesseract can easily take 10s or more for dense pages).

Source: I work in developing a competing OCR service and we keep an eye on competition (e.g. aside from Google, solutions by Azure, Amazon, Abbyy, Nuance, Cloudmersive, etc., as well as our internal product of course, which is not available externally), and they are (almost) all significantly better on Tesseract.

The only domain where Tesseract is competitive is for perfect "black text on white paper", it gives pretty poor performance when dealing with colored, distorted text, or even strong page structure effects (tables, etc.).

When I say "pretty poor" I mean: "with respect to the state-of-the-art", of course it's still enormously better than what was the state-of-the-art before deep learning came into the picture, roughly a decade ago. And for things like "search contents of a book" it's basically perfect already.

[holbue]

I agree, there are way better cloud based and proprietary OCR solutions out there. But Tesseract still seems to deliver the best results among the FOSS tools, doesn't it?

Back in the days, Cuneiform got close to Tesseract's performance, but AFAIK it wasn't developed further...

Does anyone else know other promising open-source OCR engines?