Building a Standard 3D Face Database Based on Planar Templates

Abstract:

This paper presents a new point matching method to solve the dense point-to-point alignment of scanned 3D faces. Texture maps of 3D models are generated at first by unwrapping 3D faces to 2D space. Then, we build planar templates based on the mean shape computed by a group of annotated texture map. 34 landmarks on the unwrapped texture images are located by AAM and the final correspondence is built according to the templates. Comparing to the traditional algorithms, the presented point matching method can achieve good matching accuracy and stability.

• Periodical: Applied Mechanics and Materials (Volumes 48-49)
• Pages: 280-283
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.48-49.280
• Online since: February 2011
• Authors: Xin Xin Li, Xun Gong
• Keywords: 3D Face Database, Active Appearance Model (AAM), Correspondence, Planar Template

References

[1] Blanz V, Vetter T. A morphable model for the synthesis of 3D faces[C]. Los Angeles, USA: ACM Press/Addison-Wesley Publishing Co., (1999).

[2] Gu C, Yin B, Hu Y, et al. Resampling Based Method for Pixel-wise Correspondence between 3D Faces[C]. Las Vegas, Nevada, USA: (2004).

DOI: 10.1109/itcc.2004.1286533

[3] Wang C, Yin B, Shi Q, et al. 3D Face Correspondence Based on Uniform Mesh Resampling Combined with Mesh Simplification[J]. Journal of computing information system. 2005, 11(2): 343-350.

[4] Gong X, Wang G. 3D Face Deformable Model Based on Feature Points[J]. Journal of Software. 2009, 20(3): 724-733.

DOI: 10.3724/sp.j.1001.2009.03317

[5] Gong X, Wang G. An automatic approach for pixel-wise correspondence between 3D faces[C]. Cheju Island, Korea: IEEE Computer Science, (2006).

[6] Hu Y, Yin B, Cheng S, et al. Research on Key Technology in Construction of a Chinese 3D Face Database[J]. Journal of Computer Research and Development. 2005, 42(4): 622-628.

DOI: 10.1360/crad20050414

[7] Cootes T F, Edwards G J, Taylor C J. Active appearance models[J]. IEEE Trans. Pattern Analysis and Machine Intelligence. 2001, 23(6): 681-685.

DOI: 10.1109/34.927467

[8] The BJUT-3D Large-Scale Chinese Face Database, Technical Report No ISKL-TR-05-FMFR-001, Multimedia Tech & Graphic Lab, Beijing University of Technology[R]. Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory, Beijing University of Technology, (2005).

DOI: 10.26420/austinenvironsci.2022.1075

[9] Schölkopf B, Steinke F, Blanz V. Object correspondence as a machine learning problem[C]. Bonn, Germany: (2005).

DOI: 10.1145/1102351.1102449

[10] Yin B, He Y, Sun Y, et al. Nonuniform Resampling Based on Method for Pixel-wise Correspondence Between 3D Faces[J]. Journal of Beijing University of Technology. 2007, 33(2): 213-218.