Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix confidence computation and filtering #66

Open
8 tasks
ikiss-fit opened this issue Nov 14, 2024 · 0 comments
Open
8 tasks

Fix confidence computation and filtering #66

ikiss-fit opened this issue Nov 14, 2024 · 0 comments
Assignees

Comments

@ikiss-fit
Copy link
Contributor

ikiss-fit commented Nov 14, 2024

  • Single function for confidence computation (with text) - compute in OCR engine - Copute character confidences and save with transcription in TextLine -- character confidence will be used only inside export_ALTO
  • Run the same function at the end of PageParser and when loading data with logits - Remove Update_confidences after decoder in PageParser
  • Use page parser parameter - filter_confident_lines_threshold to filter lines at the end of PageParser
  • Remove confidence computation and filtering from ALTO export
  • Move before ALTO export filtering in API code
  • Use character confidences in ALTO EXPORT
  • Add page leve confidence to PageLayout - compute it at the end of PageParser -- remove this computation from API - use this value in API.
  • IMPORTANT - Create a TEST suite!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
@ikiss-fit ikiss-fit self-assigned this Nov 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

When branches are created from issues, their pull requests are automatically linked.

1 participant