2D face database diversification based on 3D face modeling

Qun Wang; Jiang Li; Vijayan K. Asari; Mohammad A. Karim

doi:10.1117/12.894605

Translator Disclaimer

26 July 2011 2D face database diversification based on 3D face modeling

Qun Wang, Jiang Li, Vijayan K. Asari, Mohammad A. Karim

Author Affiliations +

Proceedings Volume 8001, International Conference on Applications of Optics and Photonics; 80010M (2011) https://doi.org/10.1117/12.894605
Event: International Conference on Applications of Optics and Photonics, 2011, Braga, Portugal

Abstract

Pose and illumination are identified as major problems in 2D face recognition (FR). It has been theoretically proven that the more diversified instances in the training phase, the more accurate and adaptable the FR system appears to be. Based on this common awareness, researchers have developed a large number of photographic face databases to meet the demand for data training purposes. In this paper, we propose a novel scheme for 2D face database diversification based on 3D face modeling and computer graphics techniques, which supplies augmented variances of pose and illumination. Based on the existing samples from identical individuals of the database, a synthesized 3D face model is employed to create composited 2D scenarios with extra light and pose variations. The new model is based on a 3D Morphable Model (3DMM) and genetic type of optimization algorithm. The experimental results show that the complemented instances obviously increase diversification of the existing database.

Citation Download Citation

Qun Wang, Jiang Li, Vijayan K. Asari, and Mohammad A. Karim "2D face database diversification based on 3D face modeling", Proc. SPIE 8001, International Conference on Applications of Optics and Photonics, 80010M (26 July 2011); https://doi.org/10.1117/12.894605

ACCESS THE FULL ARTICLE