rafelafrance/digi_leap_old

Issues

• Fix char_sub_matrix.py to read CSV file and not SQL

  #40 opened a year ago
  0

• Create a streamlined server install

  #39 opened 2 years ago
  0

• Speedup the OCR pipeline

  #38 opened 2 years ago
  0

• Client GUI checklist

  #37 opened 2 years ago
  0

• In setup scripts add links to ancilary databases and images

  #36 opened 2 years ago
  0

• Possible new step to the OCR pipeline

  #35 opened 2 years ago
  1

• Fill OCR table when running the gold standards

  #34 opened 2 years ago
  0

• Label reconstruction issues

  #33 opened 2 years ago
  1

• Move c++ code to rust

  #32 opened 2 years ago
  0

• Normalize characters

  #31 opened 2 years ago
  0

• Things to try in the OCR portion of the pipeline

  #30 opened 2 years ago
  0

• Add a utility to add characters to Line Align

  #29 opened 2 years ago
  1

• Add a sanity check pipe to the trait extraction part of the pipeline

  #28 opened a year ago
  0

• Add a spell check for taxon names

  #27 opened 2 years ago
  1

• We need a consistent and automatic way to handle homonyms

  #26 opened 2 years ago
  1

• Allow storing terms in a database

  #25 opened 2 years ago
  0

• SpellWell's initial load is slow

  #24 opened 2 years ago
  0

• Speed up the OCR labels script

  #23 opened 2 years ago
  0

• Echo echo echo

  #22 opened 2 years ago
  1

• The build_labels script can run in parallel

  #21 opened 2 years ago
  0

• OCR passes can be run on separate threads

  #20 opened 2 years ago
  1

• Parse text from labels

  #19 opened 2 years ago
  0

• Create a deployable pipeline

  #18 opened 2 years ago
  0

• New DB table

  #17 opened 2 years ago
  0

• Spell check is slow

  #16 opened 3 years ago
  3

• Args module

  #15 opened 2 years ago
  1

• Train OCR models

  #14 opened 3 years ago
  0

• Spell checker

  #13 opened 3 years ago
  0

• Consensus sequence heuristics

  #12 opened 3 years ago
  0

• Improve align_all function in c++ module

  #11 opened 3 years ago
  0

• Use a database to track data and results

  #10 opened 3 years ago
  1

• Line assembly improvements

  #9 opened 3 years ago
  1

• Ensemble improvement ideas

  #8 opened 3 years ago
  1

• Label detection model improvements

  #7 opened 2 years ago
  1

• Add a divider bar to OCR output images

  #6 opened 3 years ago
  1

• Improve label rotation

  #5 opened 2 years ago
  0

• Find out why we're getting many small "labels"

  #4 opened 3 years ago
  0

• Use a single font size per reconstructed label line

  #3 opened 3 years ago
  1

• Pandas adding decimal point on some numbers

  #2 opened 3 years ago
  2

• Do not use SQLite3's random() function

  #1 opened 3 years ago
  0