Facial Landmark localisation by curvature maps and profile analysis
Reviewed by Bilal Gani Taib

The detection of three dimensional (3D) landmarks by scanning surfaces is a well established method in medical science. Anatomical landmarks are visually or palpably detectable and act as reference points for clinical measurements. When measuring these landmarks with a sliding calliper no 3D image is created. This shortcoming can be overcome with surface laser scanners or parallel white light projections. The measurements of 15 residents were performed with the FastSCAN™ laser-scanning system and their curvature maps were calculated. The Koenderink shape index maps identified several landmarks from which seven commonly used distances were calculated and compared to manual measurements by way of Lin’s concordance correlation coefficient. The study measured the intercanthal distance, mouth length, nasal width, outer eye corners distance, soft tissue nasion to subnasal point distance, subnasal point to mento labial point distance and the distance between subnasal point and soft tissue pogonion. In general, measurements obtained from the scanned faces were very similar to manual measurements based on the physical face with only a few major discrepancies, this may be due inadequate image quality exacerbated by head movement during the scanning process. This preliminary study is a first step towards an automatic and objective localisation method of the anatomical landmarks and pertaining distances in clinical facial analysis. 

Facial Landmark localisation by curvature maps and profile analysis.
Carsten Lippold, Xiang Liu, Kim Wangdo, et al.
HEAD & FACE MEDICINE
2014;10:54.