Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mistral OCR

mistral.ai

Post reply on HN
Print view View original

71–80 of 450 posts

Re: Mistral OCR

#71

Post by WhitneyLand »

ChemSpider wrote: post #27

"World's best OCR model" - that is quite a statement. Are there any well-known benchmarks for OCR software?

It’s interesting that none of the existing models can decode a Scrabble board screen shot and give an accurate grid of characters.

I realize it’s not a common business case, came across it testing how well LLMs can solve simple games. On a side note, if you bypass OCR and give models a text layout of a board standard LLMs cannot solve Scrabble boards but the thinking models usually can.

Re: Mistral OCR

#72

Post by renewiltord »

opwieurposiu wrote: post #25

Related, does anyone know of an app that can read gauges from an image and log the number to influx? I have a solar power meter in my crawlspace, it is inconvenient to go down there. I want to point an old phone at it and log it so I can check it easily. The gauge is digital and looks like this: https://www.pvh2o.com/solarShed/firstPower.jpg

4o transcribes it perfectly. You can usually root an old Android and write this app in ~2h with LLMs if unfamiliar. The hard part will be maintaining camera lens cleanliness and alignment etc.

The time cost is so low that you should give it a gander. You'll be surprised how fast you can do it. If you just take screenshots every minute it should suffice.

Re: Mistral OCR

#73

Post by devmor »

notepad0x90 wrote: post #61
devmor wrote: post #20

Earlier quoted context omitted.

Good lord, I dearly hope not. That sounds like a coddled hellscape world, something you'd see made fun of in Disney's Wall-E.

hence my comment about privacy and need for legislation :) It isn't the tech that's the problem but the people that will abuse it.

While those are concerns, my point was that having everything on the internet navigated to, digested and explained to me sounds unpleasant and overall a drain on my ability to think and reason for myself.

It is specifically how you describe using the tech that provokes a feeling of revulsion to me.

Re: Mistral OCR

#75

Post by PeterStuer »

cxie wrote: post #40

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications. Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology…

I'd love to try it for my domain (regulation), but $1/1000 pages is significantly more expensive than my current local Docling based setup that already does a great job of processing PDF's for my needs.

Re: Mistral OCR

#77

Post by janalsncm »

cxie wrote: post #40

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications. Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology…

I have done OCR on leases. It’s hard. You have to be accurate and they all have bespoke formatting.

It would almost be easier to switch everyone to a common format and spell out important entities (names, numbers) multiple times similar to how cheques do.

The utility of the system really depends on the makeup of that last 5%. If problematic documents are consistently predictable, it’s possible to do a second pass with humans. But if they’re random, then you have to do every doc with humans and it doesn’t save you any time.

Re: Mistral OCR

#78

Post by coolspot »

This is $1 per 1000 pages.

For comparison, Azure Document Intelligence is $1.5/1000 pages for general OCR and $30/1000 pages for “custom extraction”.

Re: Mistral OCR

#79

Post by themanmaran »

bob1029 wrote: post #54

> It takes images and PDFs as input If you are working with PDF, I would suggest a hybrid process. It is feasible to extract information with 100% accuracy from PDFs that were generated using the mappable acrofields approach. In many domains, you have a fixed set of forms you need to process and this can be leveraged to build a custom tool for extracting the data. Only if the PDFs are unknown or were created by way o…

> Only if the PDFs are unknown or were created by way of a cellphone camera, multifunction office device, etc should you need to reach for OCR.

It's always safer to OCR on every file. Sometimes you'll have a "clean" pdf that has a screenshot of an Excel table. Or a scanned image that has already been OCR'd by a lower quality tool (like the built in Adobe OCR). And if you rely on this you're going to get pretty unpredictable results.

It's way easier (and more standardized) to run OCR on every file, rather than trying to guess at the contents based on the metadata.

Re: Mistral OCR

#80

Post by ubergeek42 »

opwieurposiu wrote: post #25

Related, does anyone know of an app that can read gauges from an image and log the number to influx? I have a solar power meter in my crawlspace, it is inconvenient to go down there. I want to point an old phone at it and log it so I can check it easily. The gauge is digital and looks like this: https://www.pvh2o.com/solarShed/firstPower.jpg

This[1] is something I've come across but not had a chance to play with, designed for reading non-smart meters that might work for you. I'm not sure if there's any way to run it on an old phone though.

[1] https://github.com/jomjol/AI-on-the-edge-device

Post reply on HN