Meeting Agenda

Date:	April 22nd, 2009
Location:	DC 1331
Time:	1:30
Chair:	Gabe Esteves

1. Changes to the Agenda - additions or deletions

2. Coffee Hour

Coffee hour last week:: Ryan- thanks!
Coffee hour this week:: Eugene
Coffee hour next week:: Volunteers?

3. Forthcoming

Date:	April 29th, 2009	May 6th, 2009	May 13, 2009	May 20th, 2009
Location:	DC 2303 1:30	DC 1304 1:30	DC 1304 1:30	DC 1304 1:30
Chair:	Zainab Meraj	Alex Pytel	Jamie Ruiz	Ryan Stedman
Technical Presentation:	Stephen Mann	Michael McCool	Zainab Meraj	Alex Pytel

4. Technical Presentation

Ryan Stedman	Title : Aiding Human Discovery of Out-of-the-Moment Handwriting Recognition Errors Abstract: Handwriting recognizers frequently misinterpret digital ink input, requiring human verification of recognizer output to identify and correct errors, before the output of the recognizer can be used with any confidence in its correctness. Technologies like Anoto pens can make this error discovery and correction task more difficult, because verification of recognizer output may occur many hours after data input, creating an ``out-of-the-moment'' verification scenario. This difficulty can increase the number of recognition errors missed by users in verification. To increase the accuracy of human verified recognizer output, methods of aiding users in the discovery of handwriting recognition errors need to be created. While this need has been recognized by the research community, no published work exists examining this problem. This talk explores the problem of creating error discovery aids for handwriting recognition

Ryan Stedman

Title : Aiding Human Discovery of Out-of-the-Moment Handwriting Recognition Errors
Abstract:
Handwriting recognizers frequently misinterpret digital ink input, requiring human verification of recognizer output to identify and correct errors, before the output of the recognizer can be used with any confidence in its correctness. Technologies like Anoto pens can make this error discovery and correction task more difficult, because verification of recognizer output may occur many hours after data input, creating an ``out-of-the-moment'' verification scenario. This difficulty can increase the number of recognition errors missed by users in verification. To increase the accuracy of human verified recognizer output, methods of aiding users in the discovery of handwriting recognition errors need to be created. While this need has been recognized by the research community, no published work exists examining this problem. This talk explores the problem of creating error discovery aids for handwriting recognition

5. Discussion Items

None so far...

6. Action Items

Meeting for April 29th will be in DC 2303

7. Conferences and Special Journal Issues

Recent Additions

Upcoming Deadlines

8. Directors' Meeting

9. Seminars and Events

2009 Apr 24, 09:00 Institute for Computer Research Short Course: Radio Systems One-Day Course, Prof. Taj Manku, Founder of Sirific
2009 Apr 24, 10:00 Human-Computer Interaction Master's Thesis Presentation: Aiding Human Discovery of Out-of-the-Moment Handwriting Recognition Errors, Ryan Stedman
2009 Apr 24, 14:00 Database Research Group PhD Seminar: Mining data streams with periodically changing distributions, Yingying Tao, PhD candidate, SCS
2009 Apr 30, 11:00 Artificial Intelligence Lab Master's Thesis Presentation: Fundamental Limitations of Semi-Supervised Learning, Tyler Lu, SCS

Also see other Math and CS postings.