Abstract
In this paper, a noble nonintrusive three-dimensional (3D) face modeling system for random-profile-based 3D face recognition is presented. Although recent two-dimensional (2D) face recognition systems can achieve a reliable recognition rate under certain conditions, their performance is limited by internal and external changes, such as illumination and pose variation. To address these issues, 3D face recognition, which uses 3D face data, has recently received much attention. However, the performance of 3D face recognition highly depends on the precision of acquired 3D face data, while also requiring more computational power and storage capacity than 2D face recognition systems. In this paper, we present a developed nonintrusive 3D face modeling system composed of a stereo vision system and an invisible near-infrared line laser, which can be directly applied to profile-based 3D face recognition. We further propose a novel random-profile-based 3D face recognition method that is memory-efficient and pose-invariant. The experimental results demonstrate that the reconstructed 3D face data consists of more than 50 k 3D point clouds and a reliable recognition rate against pose variation.
Highlights
Biometrics has recently received significant attention as an alternative to personal authentication methods such as keys, IDs, and passwords [1]
We proposed a novel 3D face acquisition and recognition system
The 3D face data acquisition system is based on a stereo vision system and an invisible line laser as a projection feature
Summary
Biometrics has recently received significant attention as an alternative to personal authentication methods such as keys, IDs, and passwords [1]. Recent 2D face recognition systems have reached a certain level of maturity under certain conditions, external and internal variations, such as pose, illumination, and expression, continue to affect its overall performance. To alleviate these variations, three-dimensional (3D) face recognition has recently received considerable attention [5,6,7,8]. To solve the correspondence problem, an active sensing technique has been proposed that projects visible features, such as lines and structured light patterns, onto the face image from emitting sources, such as a projector or laser [12,13,14,16].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
