1 Answer
- Newest
- Most votes
- Most comments
4
Amazon Rekognition cannot directly detect ID document types (ID card, passport, etc.) from all countries.
You could have a look at:
- Amazon Textract to extract information (text, fields) and combine it with business rules to guess the document type.
- Rekognition to detect a face on the document and Textract to extract the text.
If you need a custom model:
- Rekognition Custom Labels to train a model on your own annotated images.
- SageMaker to train a more advanced model (e.g., image classification) with a well-labeled dataset.
Hope it helps :)
Relevant content
asked 4 years ago
asked a year ago
asked 2 years ago
- AWS OFFICIALUpdated 3 years ago
- AWS OFFICIALUpdated 2 years ago
