We are using VNRecognizeTextRequest to detect text in documents, and we have noticed that even in some very clear and well-formatted documents, there are still instances where text blocks are missed. the live text also have the same issue.
The results detected by VNRecognizeTextRequest may miss some text blocks.
We found a case where the fast method sometimes performs better than the accurate method: using the fast method can detect more text blocks, but certain characters may be recognized incorrectly.
Recommended