Using Multi-instance Enrollment to Improve Performance of 3D Face Recognition

• NCJ Number: 304486
• Journal: Computer Vision and Image Understanding Volume: 112 Issue: 2 Dated: Nov 2008 Pages: 114-125
• Author(s): Timothy C. Faltemier; Kevin W. Bowyer; Patrick J. Flynn
• Date Published: November 2008
• Length: 12 pages
• Grant Number(s): 2005-DD-CX-K078
• Sponsoring Agency: National Institute of Justice (NIJ)
• Corporate Author: University of Notre Dame
• Publication Format: Article
• Publication Type: Research (Applied/Empirical)
• Language: English
• Country: United States of America

Annotation

This study explored the use of multi-instance enrollment as a means to improve the performance of 3D face recognition.

Abstract

Experiments were performed using the ND-2006 3D face data set, which contains 13,450 scans of 888 subjects. This is the largest 3D face data set currently available and contains a substantial amount of varied facial expression. Results indicate that the multi-instance enrollment approach outperforms a state-of-the-art component-based recognition approach, in which the face to be recognized is considered as an independent set of regions. (Publisher Abstract)