Extract QR Codes from pdf files

[nunolosada]

I don't have a technical profile, but I'm trying to test some ideas.

I'm trying to extract the QR Code string from a set of QR Codes that are represented in pdf files.
I'm trying to use docling to extract the QR Code images to process them with a JS function.
But, I'm only getting the images (base64) for each full page.

Is is possible to extract individual images from the pdf?
Is there any feature that allows to identify and extract QR Codes in pdf?

Regards

[nunolosada]

++ I'm using docling serve in a docker container.

[dolfim-ibm]

If you enable the picture classification enrichment you will easily find all the QR codes.

The list of predicted classes is in: https://github.com/docling-project/docling-core/blob/2b519f2c590be123cd25e0b748ce20e494b32512/docling_core/types/doc/labels.py#L96-L136

[nunolosada]

Many thants.

I'll try to find a way to use it.

Do you know if is it possible to extract the QR Code string using docling?