1 個回答
- 最新
- 最多得票
- 最多評論
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
已回答 2 年前
相關內容
- AWS 官方已更新 2 年前
- AWS 官方已更新 1 年前
- AWS 官方已更新 1 年前
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/.