Personalized font generation using keystroke dynamics
| dc.contributor.author | Sayah Dehkordi, Narges | |
| dc.contributor.supervisor | Nacenta, Miguel | |
| dc.date.accessioned | 2025-09-04T20:41:43Z | |
| dc.date.available | 2025-09-04T20:41:43Z | |
| dc.date.issued | 2025 | |
| dc.degree.department | Department of Computer Science | |
| dc.degree.level | Master of Science MSc | |
| dc.description.abstract | Before the advent of digital communication, personal correspondence was often handwritten, allowing people the opportunity to express themselves in their own unique style. As digital communication has become more common, typed text often lacks the personal touch that handwriting conveys. Despite the wide variety of styles in modern font design, digital font uniformity limits individual identity in typed communication. The act of typing itself, however, is a nuanced activity with distinct patterns unique to each individual. This study explores how these unique typing patterns can be leveraged to generate personalized fonts, offering a form of digital self-expression similar to handwriting. We present a system that analyzes keystroke dynamics, such as Keydown-Keydown time, Flight Time, and the spatial distribution of keys, to create customized fonts that are stable for individual participants yet unique across different participants. Using datasets from multiple universities, we preprocess and analyze typing behaviours, extracting features that are both highly discriminative and consistent. These features are then used to generate personalized fonts that visually reflect each participant’s distinct typing style. Our system demonstrates the feasibility of personalized digital communication through typing behaviour-driven font generation, offering an innovative way to enhance individuality in electronic communications. | |
| dc.description.scholarlevel | Graduate | |
| dc.identifier.uri | https://hdl.handle.net/1828/22721 | |
| dc.language | English | eng |
| dc.language.iso | en | |
| dc.rights | Available to the World Wide Web | |
| dc.subject | keystroke | |
| dc.subject | personalization | |
| dc.subject | font generation | |
| dc.subject | typing behavior | |
| dc.subject | digitalization | |
| dc.subject | digital identity | |
| dc.title | Personalized font generation using keystroke dynamics | |
| dc.type | Thesis |