12
[Feature Request] OCR: Extract specific data from zones into Fields [PR incoming]
Source: paperless-ngx/paperless-ngx#13019 · opened by @Anuril
Description This is a meta-issue for OCR improvements. A few years back, I've [suggested a solution in a comment]( that would implement "OCR Templates" for users to specify areas for specific fields. This [Feature Request ]( is basically something similar, and this [Feature Request]( is also kind of pointing in the same direction. There's this [Feature Request]( that deals with the result of the OCR'd text, this [Feature Request]( that wants better details for OCR'd Text, and this [Feature Request]( that wants better matching with complex rules. This [Feature Request ]( that wants page-specific OCR, there's discussions about OCR Plugins [here ]( [here]( and there's even the [document parser plugin framework]( that has made it into the code. Most of these issues have been closed due to no activity, and still, there's no automation of filling in fields to structure(d) data. Well - in the mean time, I've had lots of…
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature Request] Support a self-hostable remote OCR service
30 votes · 0 comments
[Feature] Optional removal of blank pages from the archive file (originals untouched)
1 vote · 0 comments
[Feature Request] OCR rendition on linked documents
2 votes · 0 comments
[Feature Request] Make Remote OCR respect `PAPERLESS_OCR_MODE` and local preprocessing options
5 votes · 0 comments
[Feature Request] Add alternative LLM based OCR
25 votes · 0 comments
No comments yet.