TOM YEH

Assistant Research Scientist
University of Maryland

Instutite of Advanced
Computer Studies (UMIACS)

Human Computer
Interaction Laboratory (HCIL)

tomyeh (at) umd.edu

4465 A.V. Williams
University of Maryland
at College Park
College Park, 20742, MD

(301) 405-9159


research
I use computer vision to automate visual tasks in the entire life cycle of interactive software including design, prototyping, development, testing, deployment, maintenance and support. My most significant research contribution so far is Sikuli Script, a GUI automation tool using screenshots. Since its release in 2010, it has been downloaded more than 200,000 times and used by a large community of users for a variety of purposes such as testing, IT automation, scraping, data transfer, and gaming.


education
2009 Ph.D. in Computer Science, MIT
Thesis: Interacting with Computers using Images for Search and Automation
2004 M.S. in Computer Science, MIT
2001 B.Sc.in Computer Science, Honor, Simon Fraser University

employment
2011-present University of Maryland - College Park, MD
Assistant Research Scientist
2009-2011 University of Maryland - College Park, MD
Post-doc Research Associate
2003-2009 MIT - Cambridge, MA
Research Assistant

award
2010 Best Paper Award
ACM Symposium on User Interface Software and Technology (UIST)
2009 Best Student Paper Award
ACM Symposium on User Interface Software and Technology (UIST)

media
2010 Screen-Capture Programming: What You See is What You Script by IEEE Computing
2010 Picture-driven Computing by MIT Press
2010 MIT Offers Picture-Centric Programming To the Masses With Sikuli by Slashdot
2010 Programming Visually with Sikuli by Computing Community Consortium (CCC)
2010 Sikuli Automates Almost Anything with Screenshot Ease by LifeHacker
2010 Sikuli: Scripting with Screenshots by PC Pro
2010 MIT Creates Picture-Driven Programming for the Masses by CIO
2010 Sikuli Can Automate Any GUI by Taking Screenshots by TUAW: The Unofficial Apple Weblog
2010 Sikuli: Create "Smart Macros" based on Screenshots by dotTech
2010 Sikuli: the Coolest Python Project I Have yet Seen by Python411
2009 Goggle Image Search Coming to Android by LinuxDevices
2004 When Databases Think by Smart Device Central
2004 Picture This by MIT Technology Review