Related Experiment Video
Updated: Jul 7, 2026
11:34
High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques
Published on: December 3, 2013
3-D face structure extraction and recognition from images using 3-D morphing and distance mapping.
Chongzhen Zhang1, Fernand S Cohen
1Robotic Vision Systems, Inc., Hauppauge, NY 11788, USA. czzhang@cbis.ece.drexel.edu
Summary
This study introduces a new method to create 3-D face models from various images, enabling accurate pose estimation and identification using a novel distance map metric for robust face recognition.
Area of Science:
- Computer Vision
- Biometrics
- 3D Reconstruction
Background:
- Accurate 3D face reconstruction from unconstrained images is challenging.
- Pose estimation and identification require robust facial representations.
Purpose of the Study:
- To develop a novel approach for 3D face structure creation from multiple, arbitrarily posed images.
- To enable accurate pose estimation and face identification using the generated 3D face model.
Main Methods:
- Morphing a generic 3D face model using cubic explicit polynomials.
- Employing a distance map metric for 3D face and pose estimation.
- Fusing geometric (distance map residual error) and intensity residual errors for identification.
Main Results:
- Successful generation of 3D face structures from unknown poses.
- Accurate pose estimation and virtual image synthesis.
- Promising face identification results on simulated and real face images, even with noise.
Conclusions:
- The proposed method effectively reconstructs 3D face structures and facilitates accurate pose estimation.
- Fusion of geometric and intensity features enhances face identification robustness.
- This approach offers a promising solution for unconstrained face recognition applications.
