Master of Science (MS)
First Committee Member
Number of Pages
Optical character recognition is the branch in computer science that involves reading text from paper and translating the images into a format that computers can manipulate. There are a lot of algorithms for finding letters and numbers, however checkboxes are often overlooked and very difficult to detect. To locate and determine if checkboxes are checked or unchecked is a very useful tool to use on forms. It is difficult to detect since there are so many ways a person can mark a checkbox. This thesis will describe a new algorithm for detecting checkboxes; Before checkboxes can be searched, certain preprocessing algorithms need to be performed on the form. The preprocessing steps are used to ensure that the width of the pixels that inscribe characters are one pixel. Not all checkmarks are drawn inside the box. Once a box is found, the coordinates are saved for further analysis.
Character; Checkbox; Detection; Optical; Recognition
University of Nevada, Las Vegas
If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to firstname.lastname@example.org and include clear identification of the work, preferably with URL.
Istle, John Michael, "Optical character recognition for checkbox detection" (2004). UNLV Retrospective Theses & Dissertations. 1724.