2013 AOCR Hackathon Wiki

Welcome to the 2013 iDigBio AOCR Hackathon Wiki

• Short URL to this hackathon wiki http://tinyurl.com/aocrhackathonwiki
• Those participating in the first iDigBio AOCR Hackathon need an iDigBio account.
• Note: This wiki page undergoing frequent updates and some participants have wiki edit permissions and will add to / update / edit these pages before, during and after the hackathon.

Links to Logistics, Communication, and Participant Information

• Participant List
  
• Call for Participation
  
• Application Form*
  
• Travel, Food, Lodging, Connectivity Logistics
  
• 2013 Hackathon Listserv, a mailing list for Hackathon Participants at aocr-hackathon-l@lists.ufl.edu

Overview of the Challenge

• 2013 iDigBio AOCR Hackathon Challenge
  • overall description of the problem
  • the specific challenge: parse OCR output to find values for these core data elements
  • read about the_metrics to be used

  "core" fields   

link to explanations and examples of the 3 data sets

  set 1: LBCC label images
  set 2: NYBG and BRIT label images
  set 3: CalBug ENT label images

link to page summarizing the rules we followed to transcribe the gold set (and others)

Text Transcription Issues

Known OCR, ML, NLP Issues and challenges

  how to get OCR to ignore a map (reduce OCR confusion)
  ... and ___ present a challenge and confuse OCR and parsing.
  figure out an algorithm that would separate images into sets with
     no handwriting, little handwriting (mostly text typed or printed), lots of handwriting

link to user interface wish list

  link labelx to apiary and symbiota
  what else?

*Thank you Nesent, Hilmar Lapp and the HIP working group for this model.