Counting Votes and the Attempt to Replicate Human Interpretation and The Code 8.7 Initiative: Using AI to End Modern Slavery
Place: Large Lecture Room
Abstract: After an initial rush to adopt purely electronic voting machines (so-called DRE's), a number of locations in the United States are returning to the use of optical scan ballots as a more trustworthy way of recording votes. While presenting a number of significant advantages, voting on paper presents some interesting technical challenges as well. These largely arise from the complexities of attempting to build machine vision systems to replicate human interpretation of markings that can be ambiguous. What seems like a relatively easy pattern recognition can serve as the basis for a rich line of research questions. I will highlight these issues in my talk, and also describe a unique collection of real ballot images from a US election a number of years ago that can serve as a useful test case. Time permitting, I will also say a few words about Code 8.7, an international collaboration aimed at using AI to end modern slavery involving participants from UN University, the UK’s Alan Turing Institute, Tech Against Trafficking, the US computing research community, other educational institutions and NGO’s, and survivors of human trafficking.
Short Bio: Dan Lopresti is a Professor of Computer Science & Engineering at Lehigh University, having recently completed 10 years as Chair of the department. He received his B.A. from Dartmouth, and his Ph.D. in computer science from Princeton. Dan’s research examines algorithmic and systems-related questions in pattern recognition, document analysis, and computer security. He has published over 150 papers and holds 24 patents. Dan serves on the Executive Committee of the International Association for Pattern Recognition and is currently IAPR’s Treasurer. He also serves on the Computing Research Association’s CCC Council, and is one of the leaders of the Code 8.7 collaboration.