←back to thread

DeepSeek OCR

(github.com)
990 points pierre | 1 comments | 20 Oct 25 06:26 UTC | HN request time: 0s | source
Show context
yoran ◴[20 Oct 25 07:22 UTC] No.45640836[source]▶
How does an LLM approach to OCR compare to say Azure AI Document Intelligence (https://learn.microsoft.com/en-us/azure/ai-services/document...) or Google's Vision API (https://cloud.google.com/vision?hl=en)?
replies(7): >>45640943 #>>45640992 #>>45642214 #>>45643557 #>>45644126 #>>45647313 #>>45667751 #
1. daemonologist ◴[20 Oct 25 14:11 UTC] No.45644126[source]▶
My base expectation is that the proprietary OCR models will continue to win on real-world documents, and my guess is that this is because they have access to a lot of good private training data. These public models are trained on arxiv and e-books and stuff, which doesn't necessarily translate to typical business documents.

As mentioned though, the LLMs are usually better at avoiding character substitutions, but worse at consistency across the entire page. (Just like a non-OCR LLM, they can and will go completely off the rails.)