Skip to content
By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post
About re:Post

Annotation of PDF document using Bounding Box

0

Hi! Is it possible to develop some kind of template for SageMaker that uses bounding boxes to annotate a PDF document? I was looking for something similar to the crowd-bounding-box HTML tag, but instead of only capturing portions of the PDF's image, I also wanted to extract data regarding the text located inside that portion, along with it's coordinates and stuff like that, so I could give context to my annotation.

  • Durga_S
    3 years ago

    I believe it could be possible, but have you tried out Amazon Textract? It is purpose built for text extraction, and provides bounding box coordinates for all text and images. You can then process the response anyway you like to extract text, paragraphs, forms etc. You can get started here - https://aws.amazon.com/textract/.

Topics
Machine Learning & AIStorage
Tags
Amazon SageMakerAmazon Augmented AIMachine Learning & AI
Language
English
asked 3 years ago1.1K views
1 Answer
0

Your usecase sounds very close to the core Textract workflow - check out this AWS ML blog post that provides a solution that generates searchable PDF's, including bounding boxes for the text and such

https://aws.amazon.com/blogs/machine-learning/generating-searchable-pdfs-from-scanned-documents-automatically-with-amazon-textract/

AWS
answered 3 years ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Relevant content