Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

SOTA IN OCR [D] (alien.top)

submitted 11 months ago by spacejunk1995@alien.top to c/machinelearning@academy.garden

8 comments fedilink hide all child comments

I am beginner in ml,how do I get myself updated with current state of OCR. If I want to get better results than Tesseract or EasyOCR ,what path should I follow.i basically want near 100% accuracy in identifying typed/digital characters and their location in image. Is this solved ?? Any guidance would be helpful 🙏🙏

top 8 comments

sorted by: hot top controversial new old

[–] EarProfessional8356@alien.top 1 points 11 months ago

Look at Meta’s Nougat OCR, use the API, run a flask server and play with it

[–] zoontechnicon@alien.top 1 points 11 months ago (1 children)

"Guys I'm new to medicine, I'm gonna solve cancer, any guidance would be helpful."

[–] AbjectDrink3276@alien.top 1 points 11 months ago

😂😂

[–] BH_Kim@alien.top 1 points 11 months ago

If you're interested in a new task, it's good for you to start by exploring Papers with Code leaderboard. You can find recent research papers related to it.

https://paperswithcode.com/dataset/textocr

[–] LinuxSpinach@alien.top 1 points 11 months ago

As of about a year ago, I haven't seen anything that really outperforms Tesseract across multiple benchmarks. You can get near 100% accuracy if the image is clean and the font isn't anything weird. But if you have image noise, you need to lower your expectations.

[–] BusinessReplyMail1@alien.top 1 points 11 months ago

Azure Form Recognizer OCR is very good.

[–] Jackrecke@alien.top 1 points 11 months ago

hey there, as a beginner in ml, staying updated on OCR is key. to surpass Tesseract or EasyOCR, focus on deep learning models, like CNNs or transformers. achieving near 100% accuracy is tough, but pre-processing, data augmentation, and model fine-tuning can help get you there. it's not fully solved, but keep experimenting and learning. good luck! 🙏

[–] sbrealxclusive@alien.top 1 points 11 months ago

have you checked out the latest research papers on OCR? following top conferences like CVPR, ICCV, and NeurIPS can help you stay updated. consider exploring deep learning models like Transformers for improved accuracy. good luck! 🚀