Comparison Study of Extraction Accuracy of 3D Facial Anatomical Landmarks Based on Non-Rigid Registration of Face Template

(1) Background: Three-dimensional (3D) facial anatomical landmarks are the premise and foundation of facial morphology analysis. At present, there is no ideal automatic determination method for 3D facial anatomical landmarks. This research aims to realize the automatic determination of 3D facial anatomical landmarks based on the non-rigid registration algorithm developed by our research team and to evaluate its landmark localization accuracy. (2) Methods: A 3D facial scanner, Face Scan, was used to collect 3D facial data of 20 adult males without significant facial deformities. Using the radial basis function optimized non-rigid registration algorithm, TH-OCR, developed by our research team (experimental group: TH group) and the non-rigid registration algorithm, MeshMonk (control group: MM group), a 3D face template constructed in our previous research was deformed and registered to each participant’s data. The automatic determination of 3D facial anatomical landmarks was realized according to the index of 32 facial anatomical landmarks determined on the 3D face template. Considering these 32 facial anatomical landmarks manually selected by experts on the 3D facial data as the gold standard, the distance between the automatically determined and the corresponding manually selected facial anatomical landmarks was calculated as the “landmark localization error” to evaluate the effect and feasibility of the automatic determination method (template method). (3) Results: The mean landmark localization error of all facial anatomical landmarks in the TH and MM groups was 2.34 ± 1.76 mm and 2.16 ± 1.97 mm, respectively. The automatic determination of the anatomical landmarks in the middle face was better than that in the upper and lower face in both groups. Further, the automatic determination of anatomical landmarks in the center of the face was better than in the marginal part. (4) Conclusions: In this study, the automatic determination of 3D facial anatomical landmarks was realized based on non-rigid registration algorithms. There is no significant difference in the automatic landmark localization accuracy between the TH-OCR algorithm and the MeshMonk algorithm, and both can meet the needs of oral clinical applications to a certain extent.

[1]  Yijiao Zhao,et al.  [Preliminary study on the method of automatically determining facial landmarks based on three-dimensional face template]. , 2022, Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology.

[2]  Xiaoyun Fu,et al.  [Deep learning-assisted construction of three-demensional facial midsagittal plane]. , 2022, Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences.

[3]  Xiangling Fu,et al.  A mathematical algorithm of the facial symmetry plane: Application to mandibular deformity 3D facial data , 2021, Journal of anatomy.

[4]  Zhouxiao Li,et al.  Reproducibility of Novel Soft-Tissue Landmarks on Three-Dimensional Human Facial Scan Images in Caucasian and Asian , 2021, Aesthetic Plastic Surgery.

[5]  Alexei I. Zhurov,et al.  An exploration of adolescent facial shape changes with age via multilevel partial least squares regression , 2021, Comput. Methods Programs Biomed..

[6]  Chee Guan Ngo,et al.  Automated craniofacial landmarks detection on 3D image using geometry characteristics information , 2019, BMC Bioinformatics.

[7]  Julie D. White,et al.  MeshMonk: Open-source large-scale intensive 3D phenotyping , 2019, bioRxiv.

[8]  Omid Ekrami,et al.  Measuring asymmetry from high-density 3D surface scans: An application to human faces , 2018, PloS one.

[9]  Rasmus R. Paulsen,et al.  Multi-view Consensus CNN for 3D Facial Landmark Placement , 2018, ACCV.

[10]  Mihran Tuceryan,et al.  The Relationship Between Hard Tissue and Soft Tissue Dimensions of the Nose in Children: A 3D Cone Beam Computed Tomography Study , 2018, Journal of forensic sciences.

[11]  D. Millett,et al.  Soft tissue changes: a comparison between changes caused by the construction bite and by successful treatment with a modified Twin-block appliance , 2018, European journal of orthodontics.

[12]  Xi Zhao,et al.  A Coarse-to-Fine Approach for 3D Facial Landmarking by Using Deep Feature Fusion , 2018, Symmetry.

[13]  G. Willems,et al.  Short-term hard and soft tissue changes after mandibular advancement surgery in Class II patients: a retrospective cephalometric study , 2017, European journal of orthodontics.

[14]  Ajmal S. Mian,et al.  Deep, dense and accurate 3D face correspondence for generating population specific deformable models , 2017, Pattern Recognit..

[15]  Mao Li,et al.  Rapid automated landmarking for morphometric analysis of three‐dimensional facial scans , 2017, Journal of anatomy.

[16]  Tancan Uysal,et al.  Reproducibility and reliability of three-dimensional soft tissue landmark identification using three-dimensional stereophotogrammetry. , 2016, The Angle orthodontist.

[17]  Ajmal S. Mian,et al.  Shape-based automatic detection of a large number of 3D facial landmarks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Jens Fagertun,et al.  3D facial landmarks: Inter-operator variability of manual annotation , 2014, BMC Medical Imaging.

[19]  Ana Maria Bettoni Rodrigues da Silva,et al.  Stereophotogrammetric evaluation of tooth-induced labial protrusion. , 2014, Journal of prosthodontics : official journal of the American College of Prosthodontists.

[20]  Jin-Hyoung Cho,et al.  A comparison study of different facial soft tissue analysis methods. , 2014, Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery.

[21]  Shu Liang,et al.  Improved detection of landmarks on 3D human face data , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[22]  Federica Marcolin,et al.  A pose-independent method for 3D face landmark formalization , 2012, Comput. Methods Programs Biomed..

[23]  A. Ayoub,et al.  Soft tissue morphology of the naso-maxillary complex following surgical correction of maxillary hypoplasia. , 2012, International journal of oral and maxillofacial surgery.

[24]  D. Vandermeulen,et al.  Spatially-dense 3D facial asymmetry assessment in both typical and disordered growth , 2011, Journal of anatomy.

[25]  H. Canter,et al.  Comparison of Facial Soft Tissue Measurements on Three-Dimensional Images and Models Obtained With Different Methods , 2010, The Journal of craniofacial surgery.

[26]  Lili Ma,et al.  Validation of a three-dimensional facial scanning system based on structured light techniques , 2009, Comput. Methods Programs Biomed..

[27]  Ashwin B. Dalal,et al.  Morphometric analysis of face in dysmorphology , 2007, Comput. Methods Programs Biomed..

[28]  J. Hicks.  Important landmarks of the orofacial complex. , 2000, Emergency medicine clinics of North America.

[29]  L. Farkas,et al.  Is photogrammetry of the face reliable? , 1980, Plastic and reconstructive surgery.

[30]  P. Claes,et al.  A Dysmorphometric Analysis to Investigate Facial Phenotypic Signatures as a Foundation for Non-invasive Monitoring of Lysosomal Storage Disorders. , 2013, JIMD reports.

[31]  Tao Jie,et al.  Markers localization of 3D face based on curvature and geometric constraints , 2009 .

[32]  V F Ferrario,et al.  Facial three-dimensional morphometry. , 1996, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.