Algorithms for Mining Distance-Based Outliers in Large Datasets
VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
Machine-assisted election auditing
EVT'07 Proceedings of the USENIX Workshop on Accurate Electronic Voting Technology
A Document Analysis System for Supporting Electronic Voting Research
DAS '08 Proceedings of the 2008 The Eighth IAPR International Workshop on Document Analysis Systems
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Style-Based Ballot Mark Recognition
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Understanding the security properties of ballot-based verification techniques
EVT/WOTE'09 Proceedings of the 2009 conference on Electronic voting technology/workshop on trustworthy elections
Implementing risk-limiting post-election audits in California
EVT/WOTE'09 Proceedings of the 2009 conference on Electronic voting technology/workshop on trustworthy elections
Efficient user-guided ballot image verification
EVT/WOTE'10 Proceedings of the 2010 international conference on Electronic voting technology/workshop on trustworthy elections
OpenScan: a fully transparent optical scan voting system
EVT/WOTE'10 Proceedings of the 2010 international conference on Electronic voting technology/workshop on trustworthy elections
An analysis of write-in marks on optical scan ballots
EVT/WOTE'11 Proceedings of the 2011 conference on Electronic voting technology/workshop on trustworthy elections
SOBA: secrecy-preserving observable ballot-level audit
EVT/WOTE'11 Proceedings of the 2011 conference on Electronic voting technology/workshop on trustworthy elections
IEEE Security and Privacy
A Gentle Introduction to Risk-Limiting Audits
IEEE Security and Privacy
| Hi-index | 0.00 |
We present OpenCount: a system that tabulates scanned ballots from an election by combining computer vision algorithms with focused operator assistance. OpenCount is designed to support risk-limiting audits and to be scalable to large elections, robust to conditions encountered using typical scanner hardware, and general to a wide class of ballot types--all without the need for integration with any vendor systems. To achieve these goals, we introduce a novel operator-in-the-loop computer vision pipeline for automatically processing scanned ballots while allowing the operator to intervene in a simple, intuitive manner. We evaluate our system on data collected from five risk-limiting audit pilots conducted in California in 2011.