CDCgov / IDWA

Intelligent Data Workflow Automation
Apache License 2.0
1 stars 1 forks source link

SPIKE: Research classification and segmentation #5

Closed zdeveloper closed 5 months ago

zdeveloper commented 6 months ago

Case Investigation form PDFs are very different and its very hard to know where to look and where the data should be, this can easily be done by a human once a form is codified into the system. Research how can this be done manually to reduce errors in the OCR process.

Acceptance Criteria Please write up a doc or a working Jupiter notebook and save it to the drive or repo and present the findings either in slack or as a techtalk in the dev sync meeting.

Additional context Texas case investigation forms