Measuring Community Consensus in Facial Characterization Using Spatial Databases and Fuzzy Logic

Spatial databases store geometric objects and capture spatial relationships that can be used to represent key features of the human face. One can search spatial databases for these objects, and seek the relationships between them, using fuzzy logic to provide a natural way to describe the human face for the purposes of facial characterization. This study focuses on community perception of short, average, or long nose length. Three algorithms were used to update community opinion of nose length. All three methods showed similar trends in nose length classification which could indicate that the effort to extract spatial data from images to classify nose length is not as crucial as previously thought since community consensus will ultimately give similar results. However, additional testing with larger groups is needed to further validate any conclusion that spatial data can be eliminated.

Name thesis:degree_name

Master of Science

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Year dc:date.available

2005

Author dc:creator

• Mastros, James Lee

Contributors dc:contributor

• Dr. Lorraine M. Parker

• steplock method
• nose length
• human face
• law enforcement
• spatial database
• criminal justice
• fuzzy logic
• Computer Sciences
• Physical Sciences and Mathematics

Statement dc:rights

• © The Author

Identifier

https://scholarscompass.vcu.edu/etd/683

OAI identifier oai:identifier

oai:scholarscompass.vcu.edu:etd-1682