Pattern-based Face Localization and Online Projector Parameterization for Multi-Camera 3D Scanning - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Pattern-based Face Localization and Online Projector Parameterization for Multi-Camera 3D Scanning

Abstract

3D face modeling is a very important and challenging task in computer vision especially in the presence of an expression variation. It plays an important role in a wide range of applications including facial animation, human-computer interaction and surgery. Current 3D face imaging solutions are often based on structured light camera/projector systems to overcome the relatively uniform appearance of skin. This paper proposes a space-time scheme for 3D face scanning, employing three calibrated cameras coupled with a non calibrated projector device. The proposed solution is a hybrid stereovision and phase-shifting approach, using two π-shifted sinusoid patterns and a texture image. It involves a pattern-based face localization approach and an online projector parameterization. The experimental results further validated the effectiveness of the proposed approach.
Not file

Dates and versions

hal-01354501 , version 1 (18-08-2016)

Identifiers

  • HAL Id : hal-01354501 , version 1

Cite

Karima Ouji, Mohsen Ardabilian, Liming Chen, Faouzi Ghorbel. Pattern-based Face Localization and Online Projector Parameterization for Multi-Camera 3D Scanning. International Conference on 3D Body Scanning Technologies, Oct 2011, Lugano, Switzerland. ⟨hal-01354501⟩
84 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More