Title
Form Removal from Election Ballots Using Image Processing
Document Type
Presentation
Publication Date
4-12-2010
Faculty Sponsor
Abstract
Vote accuracy and efficiency has become a well-known issue in the vote collection process. This project explores the possibility of applying digital image processing in counting election ballots. Current image processing techniques in the vote collection process are heavily dependent on the anticipated, geometric positioning of the vote. These techniques don’t account for markings made outside of the requested field of input. Using various form dropout techniques, however, every mark on the form can be extracted and used by the machine to make an intelligent decision. This project explores several techniques including the distance transform and gravitation based algorithms to perform form dropout, leading to data acquisition.