Title: Face Recognition based on Non-intrusive 3-D Face Modeling System
Abstract: This paper proposes a nonintrusive three-dimensional (3-D) face data acquisition and face recognition system. Although a two-dimensional (2-D) face recognition system can achieve a reliable recognition rate, its performance can be degraded by illumination and pose variation. To eliminate these factors in 2-D face recognition, 3-D face recognition which uses 3-D face data has received much attention. To acquire accurate 3-D face data, we develop the nonintrusive 3-D face acquisition system consisting of a stereo vision system and an invisible 850 nm near-infrared line laser. By using 3-D face data, 2.5-D face recognition is performed to verify the recognition performance. The experiment results show the reconstructed 3-D face data consisting of about 30,000 3-D points and the recognition rate is 96%.
Publication Year: 2009
Publication Date: 2009-07-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot