Questions tagged with Amazon Textract
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.
I was wondering whether your service can automatically recognise reports in a searchable PDF document, bookmark them according to date and tile then sort them in chronological order?
1
answers
0
votes
229
views
asked 10 months agolg...
Hi I am using Textract on images of tables and noticed quite poor performance on denser tables. Are there any parameters I can tweak to boost this performance in the example below? I'm surprised that...
2
answers
1
votes
235
views
asked 10 months agolg...
Hello,
I'm extracting header and table information from a PDF using Textract and need to combine them into an XML file. Currently, I'm using "AnalyzeDocument - Forms" for the header and...
1
answers
0
votes
192
views
asked 10 months agolg...
Hello,
Could you please detail the differences among Textract and Rekognition services regarding text detection in images ?
Are they used in different use cases ? Do they have the same accuracy in...
1
answers
0
votes
796
views
asked a year agolg...
Hi everyone, I'm currently working with textract and I'm not sure where to retrieve my "textract client" which I'm asked for in the python script. Is it the same as my IAM profile, or is it the...
2
answers
0
votes
287
views
asked a year agolg...
Please find below the code, I've replaced confidential contents with **.
```
import re
# boto3 client
textract = boto3.client(
'textract',
region_name='**',
aws_access_key_id='**',
...
1
answers
0
votes
357
views
asked a year agolg...
Of course, the code works on my local development environment. But when hosted in the cloud, I get this error:
**AccessDeniedException: User:...
2
answers
0
votes
338
views
asked a year agolg...
Hi.
Is the DetectDocumentText job something that should recognize for each WORD if it is HANDWRITING or PRINTED? I noticed the following behavior with different documents I used:
* If document is...
1
answers
0
votes
228
views
asked a year agolg...
I am using Amazon Textract Signature Extraction. In the response I am not getting Block type Signature while extracting the signature from the image. Is there any other solution for getting the...
2
answers
0
votes
228
views
asked a year agolg...
Hi team,
Hope you are doing well,
I am using analyse expense of AWS Textract, when passing the pdf file for getting the extracted response, the json object doesn't return the group properties as...
1
answers
0
votes
204
views
asked a year agolg...
How can I implement a feedback loop in analyze expense API in textract. I see there is a way to create human review workflow for analyze document API...
1
answers
0
votes
264
views
asked a year agolg...
I am processing thousands of documents using textract. But since textract has a limit of running 100 jobs in parallel, I want to make sure that only 100 documents are sent to textract at any...
1
answers
0
votes
346
views
asked a year agolg...