Facial Model Deformation Based on Landmarks Using Laplacian

Ongki Permono Aji, I. Ketut Eddy Purnama, Eko Mulyanto Yuniarno

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

1 Citation (Scopus)

Abstract

Reconstructing a 3D face model from an unknown skull provides many benefits in the fields of archeology, anthropology, and forensic investigation. Computer systems for 3D facial reconstruction provide a big advantage in reducing time consumption. In this paper, we propose computer-based 3D face reconstruction for Indonesian from CT Scan images using facial model deformation which is limited by knowledge of soft tissue thicknesses. First, we prepare supporting data in the form of general face models and FSTTs for Indonesians. Then we set landmarks on the unknown skulls. By adding FSTT to the skull landmarks, we get landmark coordinates from predicted face. Finally, we performed Laplacian deformation on the face model so that its shape and size matched the landmark coordinates of the predicted face.

Original languageEnglish
Title of host publication2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728129655
DOIs
Publication statusPublished - Nov 2019
Event2nd International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Surabaya, Indonesia
Duration: 19 Nov 201920 Nov 2019

Publication series

Name2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding
Volume2019-November

Conference

Conference2nd International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019
Country/TerritoryIndonesia
CitySurabaya
Period19/11/1920/11/19

Keywords

  • FSTT
  • landmark
  • laplacian
  • point cloud
  • surface deformation

Fingerprint

Dive into the research topics of 'Facial Model Deformation Based on Landmarks Using Laplacian'. Together they form a unique fingerprint.

Cite this