IssueTracker

This will create a public issue which anybody can view and comment on.

Please provide as much information as possible. At least, this should include a description of your issue and steps to reproduce the problem. If possible please provide a summary of what steps or workarounds you have already tried, and any docs or articles you found (un)helpful.

Problem you have encountered:

Document AI OCR Processor often produces overlapping bounding boxes in the images/files it processes. This inconsistency in the extracted data is caused by the creation of new data using information from the overlapping boxes.

I have attempted to resolve this issue by increasing the image/file quality, brightness, and size, as well as adjusting the OCR Processor settings. Unfortunately, these measures have not been effective. Notably, the majority of the overlapping bounding boxes are vertically aligned.


What you expected to happen:

Extract the information from image/file without overlapping the boxes and mixing information extracted.

Steps to reproduce:

Create an OCR Processor on Document AI
Upload an image/file to process
Run the processing step
Get the processed files/images with overlapping boxes

I will attach some files that I have tested and its results (tested resources on PDF and JPG files)