Skip to main content

Research of the Ear Reconstruction Based on the Poisson Image Blending

  • Conference paper
  • First Online:
Digital TV and Wireless Multimedia Communication (IFTC 2017)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 815))

  • 1790 Accesses

Abstract

Due to the undesirable reconstruction result of the ear part in the 3D face reconstruction which based on single image, we propose an ear reconstruction approach based on the Poisson image blending method. First of all, the 3D face shape is reconstructed from the single frontal image by fitting the sparse morphable model. Then the cylindrical expansion approach and the elliptical skin color criterion are combined in order to utilize for the texture reconstruction and correction process. Finally, the Poisson image blending method is selected to carry out the second recovery for the ear part. The experiment results demonstrate that our approach not only ensure a fast and simplified reconstruction process but also efficiently improve the undesirable reconstruction result in the face profile especially the ear part, which has existed in some 3D face modeling technologies. Meanwhile, it further enhances the sense of reality of the reconstruction result.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.00
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Xu, C.H., Wang, Y.H., Tan, T.N.: Overview of research on 3D face modeling. J. Image Graph. 9(8), 893–903 (2004)

    Google Scholar 

  2. Horn, B.K.P.: Height and gradient from shading. Int. J. Comput. Vis. 5(1), 37–75 (1990)

    Article  Google Scholar 

  3. Blanz, V., Vetter, T.: Face recognition based on fitting a 3D morphable model. IEEE Trans. Patt. Anal. Mach. Intell. 25(9), 1063–1074 (2003)

    Article  Google Scholar 

  4. Li, X.: Research of 3D Modeling Based on the Single Frontal Image. Soochow University (2016)

    Google Scholar 

  5. Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Patt. Anal. Mach. Intell. 11(6), 567–585 (2002)

    Article  MATH  Google Scholar 

  6. Rez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM Trans. Graph. 22(3), 313–318 (2003)

    Article  Google Scholar 

  7. Yin, B., Sun, Y., Wang, C., et al.: BJUT-3D large scale 3D face database and information processing. J. Comput. Res. Dev. 46(6), 1009–1018 (2009)

    Google Scholar 

  8. Ran, H.Z., Zhou, J.L., Wang, L.: Face detection in color image. Asia Pac. J. Anthropol. 10(1), 56–58 (2009)

    Article  Google Scholar 

  9. Tian, Y.: 3D Face Reconstruction Based on Single Frontal Face Image. Chongqing University (2011)

    Google Scholar 

  10. Deng, Q.P.: 3D Face Reconstruction Based on a Single Image and Statistical Model. Shanghai Jiao Tong University (2010)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jianling Hu .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, Y., Zhang, Q., Wang, B., Li, X., Hu, J. (2018). Research of the Ear Reconstruction Based on the Poisson Image Blending. In: Zhai, G., Zhou, J., Yang, X. (eds) Digital TV and Wireless Multimedia Communication. IFTC 2017. Communications in Computer and Information Science, vol 815. Springer, Singapore. https://doi.org/10.1007/978-981-10-8108-8_41

Download citation

  • DOI: https://doi.org/10.1007/978-981-10-8108-8_41

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-10-8107-1

  • Online ISBN: 978-981-10-8108-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics