2013 AOCR Hackathon Wiki: Difference between revisions

Revision as of 22:35, 10 January 2013

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.

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

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)

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.

@@ Line 31: / Line 31: @@
 [[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