Al usar AWS re:Post, aceptas las AWS re:Post Términos de uso
AWS re:Postre: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
    hace 2 años

    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/.

Temas
Aprendizaje automático e IA
Etiquetas
Amazon Augmented AIAmazon SageMakerAprendizaje automático e IA
Idioma
English
PedroCavadas
preguntada hace 2 años715 visualizaciones
1 Respuesta
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
dccn-aws
respondido hace 2 años

No has iniciado sesión. Iniciar sesión para publicar una respuesta.

Una buena respuesta responde claramente a la pregunta, proporciona comentarios constructivos y fomenta el crecimiento profesional en la persona que hace la pregunta.

Pautas para responder preguntas

Contenido relevante