Clemson University
Transforming Character Faces based on Perceived Personality Traits
Abstract
dc:description.abstractThe ability to read other human's faces is a crucial part of everyday life. Subconsciously, the human brain analyzes someone's face within the first few seconds of seeing it, making a variety of conclusions ~\cite{FacePerp} such as gathering information about emotional state and assuming character traits this person might possess. The purpose of this thesis is to create a tool that allows a user to alter features of a character's three dimensional (3D) face mesh to look increasingly or decreasingly like the character possesses certain personality traits. Using a sample set of randomly generated faces, a survey is conducted to rate if the given face, or associated character, possesses a set of chosen characteristics. The characteristics included in this study, i.e. trustworthiness, were chosen based on previous studies investigating the association of facial attributes to personality traits based solely on rapid visual appraisal. Resulting character face meshes produced with the presented work exhibit the same character identity but with perceived traits amplified or decreased. This may be useful in production as a tool to design character faces with particular traits in mind, leveraging human bias of viewers or players.
Degree
thesis:*- Name thesis:degree_name
- Master of Fine Arts (MFA)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Digital Production Arts
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Porter, Kara
- Contributors dc:contributor
-
- Eric Patterson
- Rodney Costa
- Jerry Tessendorf
Subjects
dc:subject × 9Identifiers
dc:identifier.*- Repository record dc:identifier
- https://open.clemson.edu/all_theses/3946