Photo-realistic 3D human face modeling based on radial-basis function networks

Li Mao, Yang Yu Fan, Yan Hui Huang, Tao Lei, Guo Yun Lv

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes an efficient method for modeling photo-realistic 3D human face from two orthogonal photos taken from front and side views. The method utilizes active shape model based on RGB color space to extract facial boundaries and detect feature points from the orthogonal photos. The previously constructed generic models are modified by exploiting the abilities of radial-basis function networks and considering the feature points detected from the orthogonal photos. Based on image mosaic, the Laplacian pyramid is developed to obtain 360 degree seamless texture, in the manner of feature fusion. Simulation results show that the proposed method outperforms the conventional methods with respect to the modeling precision, and that the 3D faces generated by the proposed method are both smoothing and photo-realistic.

Original languageEnglish
Title of host publicationProceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010
Pages2819-2823
Number of pages5
DOIs
StatePublished - 2010
Event2010 3rd International Congress on Image and Signal Processing, CISP 2010 - Yantai, China
Duration: 16 Oct 201018 Oct 2010

Publication series

NameProceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010
Volume6

Conference

Conference2010 3rd International Congress on Image and Signal Processing, CISP 2010
Country/TerritoryChina
CityYantai
Period16/10/1018/10/10

Keywords

  • Active shape model
  • Face modeling
  • Laplacian pyramid
  • Radial-basis function networks
  • RGB color space

Fingerprint

Dive into the research topics of 'Photo-realistic 3D human face modeling based on radial-basis function networks'. Together they form a unique fingerprint.

Cite this