Questions tagged with Amazon Textract
Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents.
Content language: English
Select up to 5 tags to filter
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
Hi,
It would be great if we could get advice on an account service quota limit which is beginning to be a bottleneck for our system. The Amazon Textract Async DocumentTextDetection throttle limit of...
Hi Team,
I'm experiencing an issue with Amazon Textract when processing documents that contain both vernacular (non-English) and English handwritten text. The OCR results for the English handwritten...
Hi,
I am experimenting with Textract and have been training the model using the Web front end on my Dev Account and have created an "Adapter" etc
1. How and What is needed for the model to be...
I've been trying to extract tables asynchronously from a multi-page pdf file, however it appears that only the table on the first page is returned. I successfully receive a jobID and pass the...
I'm trying to extract tables asynchronously from a pdf document, using Textract with the Javascript V3 sdk. I successfully get a jobID from the StartDocumentAnalysisCommand, however when calling...
Hi,
textract is very powerful, but even a 30 degree rotation in texts, such as a dates in a table rotated for shortening space, renders it unrecognizable.
Any remedies?
Thank you
Hi,
I have created/trained an Adapter using the Console/wizard but am running into issues calling it from code/lambda in Python (3.12)
1. Do I have to **specify the same Queries** used in the...
I tried various ways, It is hard for me to figure out where to get an API key and to create a lamda function. Please help me to do this
The textract pricing for synchronous commands is pretty clear (1 API call that gets billed), but in case of asynchronous commands, there are at least two API calls necessary:
1. start the process of...
Hello, I'm trying to extract just the summary fields from a `startExpenseAnalysis` call with Textract (ignore the line item fields) , is it that possible?
I'm trying to reduce the response time less...
is the sync analyzedocuemnt api from** python SDK **encrypted by TLS by default? this will be enough for HIPAA compliance as far as encryption in transmit is concerned?
if not whats the best/easiest...
Hello, aws people.
I am extracting the content of pdf with Amazon textract.
I know Amazon textract doesn't support page numbers.
But I need to make sure I can extract page numbers together from the...