Off-campus Eastern Washington University users: To download EWU Only theses, please use the following link to log into our proxy server with your EWU NetID and password.

Non-EWU users: Please talk to your local librarian about requesting this thesis through Interlibrary loan.

Date of Award

2014

Document Type

Thesis: EWU Only

Degree Name

Master of Science (MS) in Computer Science

Department

Computer Science

Abstract

Identification of an individual has been a long standing problem in human existence. It is clear from the rising rates of identity theft and misappropriation of services that current methods employed to identify individuals is ineffectual. The most common way people identify other individuals is via recognition of the subjects face. The speed and accuracy with which one person can identify another person is uncanny leading to the development automated facial recognition systems. The vast majority of these systems use two-dimensional (2D) images imagery to perform facial recognition with limited success. The use of 2D imagery has limitations which cannot be overcome therefore three-dimensional (3D) facial recognition systems have become the focus of study. The imaging systems used to capture 3D facial imagery is complex, expensive and requires a degree of cooperation from the subject. This paper proposes the use of older photogrammetry techniques to capture 3D facial imagery thereby eliminating the need for specialized 3D imaging equipment. In addition the camera system, once configured, does not require an operator nor does it require undo cooperation of the subject.

Comments

Typescript. Vita.

Creative Commons License


This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS