Comparing 3D Descriptors for Local Search of Craniofacial Landmarks

  • Federico M. Sukno
  • John L. Waddington
  • Paul F. Whelan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7432)


This paper presents a comparison of local descriptors for a set of 26 craniofacial landmarks annotated on 144 scans acquired in the context of clinical research. We focus on the accuracy of the different descriptors on a per-landmark basis when constrained to a local search. For most descriptors, we find that the curves of expected error against the search radius have a plateau that can be used to characterize their performance, both in terms of accuracy and maximum usable range for the local search. Six histograms-based descriptors were evaluated: three describing distances and three describing orientations. No descriptor dominated over the rest and the best accuracy per landmark was strongly distributed among 3 of the 6 algorithms evaluated. Ordering the descriptors by average error (over all landmarks) did not coincide with the ordering by most frequently selected, indicating that a comparison of descriptors based on their global behavior might be misleading when targeting facial landmarks.


Local Search Local Accuracy Spin Image Search Radius Local Reference Frame 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hennessy, R., Baldwin, P., Browne, D., Kinsella, A., Waddington, J.: Frontonasal dysmorphology in bipolar disorder by 3D laser surface imnaging and geometric morphometrics: Comparison with schizophrenia. Schizophr Res. 122, 63–71 (2010)CrossRefGoogle Scholar
  2. 2.
    Sharifi, A., Jones, R., Ayoub, A., et al.: How accurate is model planning for orthognathic surgery. Int. J. Oral. Max. Surg. 37, 1089–1093 (2008)CrossRefGoogle Scholar
  3. 3.
    Bowyer, K., Chang, K., Flynn, P.: A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recogn. Comput. Vis. Image Und. 101, 1–15 (2006)CrossRefGoogle Scholar
  4. 4.
    Plooij, J., Swennen, G., Rangel, F., et al.: Evaluation of reproducibility and reliability of 3D soft tissue analysis using 3D stereophotogrammetry. Int. J. Oral. Max. Surg. 38, 267–273 (2009)CrossRefGoogle Scholar
  5. 5.
    Aynechi, N., Larson, B., Leon-Salazar, V., et al.: Accuracy and precision of a 3D anthropometric facial analysis with and without landmark labeling before image acquisition. Angle Orthod. 81, 245–252 (2011)CrossRefGoogle Scholar
  6. 6.
    Dibeklioglu, H., Salah, A., Akarun, L.: 3D faceial landmarking under expression, pose, and occlusion variations. In: Proc. BTAS, pp. 1–6 (2008)Google Scholar
  7. 7.
    Segundo, M., Silva, L., Bellon, et al.: Automatic face segmentation and facial landmark detection in range images. IEEE T. Syst. Man Cy B: Cybernetics 40, 1319–1330 (2010)CrossRefGoogle Scholar
  8. 8.
    Gupta, S., Markey, M., Bovik, A.: Antopometric 3D face recognition. Int. J. Comput. Vision 90, 331–349 (2010)CrossRefGoogle Scholar
  9. 9.
    Szeptycki, P., Ardabilian, M., Chen, L.: A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking. In: Proc. BTAS, pp. 1–6 (2009)Google Scholar
  10. 10.
    Passalis, G., Perakis, N., Theoharis, T., et al.: Using facial symm to handle pose variations in real-world 3D face recogn. IEEE T. Pattern Anal. 33, 1938–1951 (2011)CrossRefGoogle Scholar
  11. 11.
    Salti, S., Tombari, F., Stefano, L.: A performance evaluation of 3D keypoint detectors. In: Proc. 3DimPVT, pp. 236–243 (2011)Google Scholar
  12. 12.
    Bronstein, A., Bronstein, M., Castellani, U., et al.: SHREC 2010: robust correspondence benchmark. In: Proc. 3DOR (2010)Google Scholar
  13. 13.
    Creusot, C., Pears, N., Austin, J.: Automatic keypoint detection on 3D faces using a dictionary of local shapes. In: 3DimPVT, pp. 204–211 (2011)Google Scholar
  14. 14.
    Romero-Huertas, M., Pears, N.: Landmark localisation in 3D face data. In: Proc. AVSS, pp. 73–78 (2009)Google Scholar
  15. 15.
    Rusu, R., Cousins, S.: 3D is here: Point cloud library (PCL). In: Proc. ICRA, pp. 1–4 (2011)Google Scholar
  16. 16.
    Johnson, A., Hebert, M.: Using spin images for efficient object recognition in cluttered 3D scenes. IEEE T. Pattern Anal. 21, 433–449 (1999)CrossRefGoogle Scholar
  17. 17.
    Frome, A., Huber, D., Kolluri, R., Bülow, T., Malik, J.: Recognizing Objects in Range Data Using Regional Point Descriptors. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 224–237. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  18. 18.
    Tombari, F., Salti, S., Stefano, L.D.: Unique shape context for 3D data description. In: Proc. 3DOR, pp. 57–62 (2010)Google Scholar
  19. 19.
    Tombari, F., Salti, S., Stefano, L.D.: Unique signature of histograms for local surface description. In: Proc. ECCV, pp. 356–369 (2010)Google Scholar
  20. 20.
    Rusu, R., Blodow, N., Marton, Z., et al.: Aligning point cloud views using persistent feature histograms. In: Proc. IROS, pp. 3384–3391 (2008)Google Scholar
  21. 21.
    Rusu, R., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration. In: Proc. ICRA, pp. 3212–3217 (2009)Google Scholar
  22. 22.
    Hennessy, R., Kinsella, A., Waddington, J.: 3D laser surface scanning and geometric morphometric analysis of craniofacial shape as an index of cerebro-craniofacial morphogenesis: initial applic to sexual dimorph. Biol. Psychiat. 51, 507–514 (2002)CrossRefGoogle Scholar
  23. 23.
    Farkas, L.: Anthropometry of the head and face, 2nd edn. Raven Press, New York (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Federico M. Sukno
    • 1
    • 2
  • John L. Waddington
    • 2
  • Paul F. Whelan
    • 1
  1. 1.Centre for Image Processing & AnalysisDublin City UniversityDublinIreland
  2. 2.Molecular & Cellular TherapeuticsRoyal College of Surgeons in IrelandDublinIreland

Personalised recommendations