Award Date

1-1-2004

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Committee Member

Evangelos Yfantis

Number of Pages

66

Abstract

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.

Keywords

Character; Checkbox; Detection; Optical; Recognition

Controlled Subject

Computer science

File Format

pdf

File Size

1331.2 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

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 digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Download


COinS