Date of Award


Degree Type


Degree Name

Master of Science


Computer Science


Dr. Stephen M. Watt


At the present time, with the technology that many portable devices have, pen-based input is widely supported and input can be done through handwriting rather than just by typing. While character recognition and other input issues are the main consideration with these devices, there are many interesting output issues related to digital ink. This thesis investigates the questions of handwriting neatening and personal handwriting fonts. We use the notion of “character metrics”, .which refer to the location and size of various features, such as ascender height and character width. Recording these features for handwritten characters allows for input and output transformations and may help with recognition in a 2-dimensional setting such as for mathematical handwriting recognition. To be able to create personalized handwriting fonts, we have constructed a tool to collect samples where lines related to the characters metrics can be recorded. Handwriting always comes with variations in alignment and size so certain measurements based on these metrics can be extracted to perform the desired transformations to obtain a set of samples in a normalized form.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.