iDigBio Augmenting OCR Hackathon
February 13-14, 2013, in Fort Worth, Texas
Be a part of helping to get "dark data" out of millions of museum cabinets and into online databases!
Integrated Digitized Biocollections, iDigBio, along with the Botanical Research Institute of Texas (BRIT), are hosting their 1st Hackathon, to be held February 13-14, 2013, at the Botanical Research Institute of Texas (BRIT).
The iDigBio Augmenting Optical Character Recognition Working Group (AOCR) invites you to help us improve OCR output and natural language parsing of natural history museum's specimen label data.
Who can participate? We are looking for individuals interested in Natural Language Parsing, Optical Character Recognition, User Interfaces, and use of these tools by scientists and the public to access natural history museum collections data. This includes scientists, citizen scientists, information scientists, software engineers, students, faculty, post-docs, and staff of both genders and from different backgrounds. While we need hackers who write great code, we also seek individuals who have experience with writing, applying and optimizing natural language processing algorithms, image processing and analysis, as well as designing user interfaces, testing software, developing tutorials, and documenting user experiences. We are striving to engage the Information Science community in our natural history collections digitization efforts.
HOW TO APPLY
Apply at: http://tinyurl.com/iDigBioAOCRHackathon
Early registration ends November 30, 2012, at 11:55 P.M. Space is limited to 20 people.
Partial support (and, if funds allow, full support) for travel, food and lodging will be available to each successful applicant who indicates need. Applications from women and members of underrepresented groups are particularly welcome.
To consider how you might be able to contribute, please review the Google doc at http://tinyurl.com/aocrHack or contact one of the members of the iDigBio AOCR working group:
Working Group Members to contact:
- Bryan Heidorn, email@example.com
- Edward Gilbert, firstname.lastname@example.org
- Jason Best, email@example.com
Note: this hackathon is being held concurrent with iConference 2013 in Fort Worth, where the iDigBio AOCR Working Group will present a half-day workshop on February 12th: Help iDigBio Reveal Hidden Data: iDigBio Augmenting OCR Working Group Needs You!
Many thanks to NESCent, Hilmar Lapp and HIP working group and many others for help with this effort.