research-digitized-rhinoplasty / 3D-Facial-Landmark-Detection

Detecting Facial Landmarks on 3D Models Based on Geometric Properties

Home Page:https://digitized-rhinoplasty.com/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

3D Facial Landmark Detection

Detecting Facial Landmarks on 3D Models Based on Geometric Properties

Face Landmark Detection algorithms on 3D Face Scans are presented along with pseudocode. Pseudocode from literature for some of the landmarks are listed as well.

This code repository includes pseudocode and Phyton implementations for the following facial landmarks:

  • Alar Base Junction/Alar Crease - left/right (ac)
  • Alar Rim’s Highest Point - left/right (armax)
  • Alare/Alar Flare - left/right (al)
  • Cheilion - left/right (ch)
  • Columellar Break Point (cb)
  • Columellar Rim - left/right (cmin)
  • Endocanthion/Medial Canthus - left/right (en)
  • Exocanthion/Lateral Canthus - left/right (ex)
  • Glabella (g)
  • Labiale Superius (ls)
  • Lateral helix of ear - left/right (la)
  • Maxillofrontale - left/right (ma)
  • Menton/Gnathion (me)
  • Nasal Parenthesis - left/right (np)
  • Nasion/Radix (n)
  • Pronasale/Tip (prn)
  • Sellion
  • Stomion (sto)
  • Subalare - left/right (sbal)
  • Subnasale - left/right
  • Subnasale (sn)
  • Supratip Break Point (s)
  • Tip Defining Point - left/right (td)
  • Trichion
  • Zygion (left/right)

The algorithms assume that the face 3D models are placed in the correct pose and orientation on the x, y, and z coordinate systems, facing the z-axis.

This study has been published in IEEE Access, please use the following to cite:

  • O. Topsakal, T. C. Akinci, J. Murphy, T. L. -J. Preston and M. M. Celikoyar, "Detecting Facial Landmarks on 3D Models Based on Geometric Properties—A Review of Algorithms, Enhancements, Additions and Open-Source Implementations," in IEEE Access, vol. 11, pp. 25593-25603, 2023, doi:10.1109/ACCESS.2023.3255099.

About

Detecting Facial Landmarks on 3D Models Based on Geometric Properties

https://digitized-rhinoplasty.com/

License:GNU General Public License v3.0


Languages

Language:Jupyter Notebook 100.0%