Kinda reminds me of PaddleOCR.
Would be awesome if DeepSeek OCR could be integrated into a mobile app someday. That’d make OCR way more convenient!
DeepSeek OCR
41–50 of 252 posts
Re: DeepSeek OCR
#42My impression is that OCR is basically solved at this point.
The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product.
I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content in Markdown under some additional formatting instructions. That will cost you around $0.20 for 1000 pages in batch mode and the results have been great.
I'd be interested to hear where OCR still struggles today.
Re: DeepSeek OCR
#43Earlier quoted context omitted.
I'm not really sure if that's an accurate summary of the state of the art, [0] is a better overview. In short, SOTA multi-modal LLMs are the best option for handwriting, nearly anything is good at printed text, for printed media, specialty models from hyperscalers are slightly better than multi-modal LLMs. [0] https://research.aimultiple.com/ocr-accuracy/
I see it confirms what I wrote state of art is “not using tessaract anymore” and I think bunch of commercial solutions are stuck with tessaract.
I assume Tesseract has the advantage of being able to give a confidence score?
Re: DeepSeek OCR
#44My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
> My impression is that OCR is basically solved at this point.
Not really in practice to me. Especially they still struggle with Table format detection.
Re: DeepSeek OCR
#45My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
Technically not OCR, but HTR (hand-written text/transcript recognition) is still difficult.
LLMs have increased accuracy, but their mistakes are very hard to identify because they just 'hallucinate' text they cannot digitize.
Re: DeepSeek OCR
#46My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
> My impression is that OCR is basically solved at this point. Not really in practice to me. Especially they still struggle with Table format detection.
This.
Any complex parent table span cell relationship still has low accuracy.
Try the reverse, take a complex picture table and ask Chatgpt5, claude Opus 3.1, Gemini Pro 2.5 to produce a HTML table.
They will fail.
Re: DeepSeek OCR
#47My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
If you can accept that the machine just make up what it doesn't recognize instead of saying "I don't know," then yes it's solved.
(I'm not being snarky. It's acceptable in some cases.)
Re: DeepSeek OCR
#48My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
No way it's solved. try to make OCR over a magazine with creative layouts. Not possible. I have a collection of vintage computer magazines and from time to time I try to OCR them whith the state of the art mechanisms. All of them requiere a lot of human intervention
Re: DeepSeek OCR
#49Earlier quoted context omitted.
> My impression is that OCR is basically solved at this point. Not really in practice to me. Especially they still struggle with Table format detection.
This. Any complex parent table span cell relationship still has low accuracy. Try the reverse, take a complex picture table and ask Chatgpt5, claude Opus 3.1, Gemini Pro 2.5 to produce a HTML table. They will fail.
Maybe I misunderstood the assignment but it seems to work for me.
https://chatgpt.com/share/68f5f9ba-d448-8005-86d2-c3fbae028b...
Edit: Just caught a mistake, transcribed one of the prices incorrectly.
Re: DeepSeek OCR
#50My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
No way it's solved. try to make OCR over a magazine with creative layouts. Not possible. I have a collection of vintage computer magazines and from time to time I try to OCR them whith the state of the art mechanisms. All of them requiere a lot of human intervention
do you have an example of a particularly tricky one?