"NSF Grant Supports Ballot Integrity Research"

Rice University, Texas A&M University, and the University of Alabama (UAB) at Birmingham will use Artificial Intelligence (AI) to examine the robustness and security of election systems that read hand-marked paper ballots. The National Science Foundation (NSF) awarded a grant to Rice's Dan Wallach, Texas A&M's Nitesh Saxena, and UAB's Chengcui Zhang to develop Bubble Aid, an AI system that can read hand-written ballots. The system will use modern computer vision and Machine Learning (ML) techniques to recognize hand-marked bubble targets more effectively than existing systems after training on data from millions of actual ballots. Bubble Aid has the potential to improve vote tabulation efficiency and security by directing election officials' attention to ambiguous ballots that require the most manual attention. This article continues to discuss the Bubble Aid system aimed at boosting the efficiency and security of election systems.

Rice University reports "NSF Grant Supports Ballot Integrity Research"