Special issue on registration and fusion of range images
Computer Vision and Image Understanding - Registration and fusion of range images
Feature subset selection using a new definition of classifiability
Pattern Recognition Letters
Matching 2.5D Face Scans to 3D Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time 3D face recognition using line projection and mesh sampling
EG 3DOR'11 Proceedings of the 4th Eurographics conference on 3D Object Retrieval
| Hi-index | 0.00 |
In this paper we discuss methods for 3D reconstruction from a single 2D image using multiple stripe line projection. The method allows 3D reconstruction in 40 milliseconds, which renders it suitable for on-line reconstruction with applications into security, manufacturing, medical engineering and entertainment industries. We start by discussing the mathematical fundamentals of 3D reconstruction and the required post-processing operations in 3D to render the models suitable for biometric applications such as noise removal, hole filling, smoothing and mesh subdivision. The incorporation of data acquired as 3D surface scans of human faces into such applications present particular challenges concerning identification and modelling of features of interest. The challenge is to accurately and consistently find predefined features in 3D such as the position of the eyes and the tip of the nose for instance. A method is presented with recognition rates up to 97% and a preliminary sensitivity analysis is carried out concerning reconstructed and subdivided models.