Skip to main content
SpringerLink
Log in

A robust analysis, detection and recognition of facial features in 2.5D images

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

A robust technique for recognition of 3D faces which performs well with face images with various poses, expressions and occlusions. In this method, the face images represented in 3D mesh format are smoothed using trilinear interpolation and then converted to 2.5D image or range images. Nose-tip which is the most prominent feature on human face is detected first on the corner points selected by 3D Harris corner and curvedness at those corner points. K-Means clustering is applied to group those corner points in 2 groups. The cluster of points with larger curvedness values represents the possible locations of nose-tip. Nose-tip is finally localized using Mean-Gaussian curvature values of the prospective corner points in that cluster. Using the nose-tip location, other facial landmarks namely corners of the eyes and mouth are located and a facial graph is generated. The dimensionality of 2.5D feature space is that, depth values are stored at each (x, y) grid of the 2.5D image, so a 3D face image uses some function to map the depth value at any pixel position to the intensity with which that pixel will be displayed. Here finally extracted features for each subject is of dimensionality [1 × 21], taking into account the Euclidean distances in three dimensional form between each feature points detected automatically. Taking Euclidean distances between all pairs of landmark points as features, face images are classified using Multilayer Perceptron (MLP), as well as Support Vector Machines (SVM). Maximum recognition rates of 75 and 87.5 % have been obtained in case of Bosphorus Databases, 62.5 and 87.5 % in case of GavabDB databases, 75 and 87.5 % in case of Frav3D Databases by Multilayer Perceptron and Support Vector Machines respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig 24
Fig. 25
Fig. 26
Fig. 27
Fig. 28
Fig. 29
Fig. 30

Similar content being viewed by others

References

  1. Akima H (1978) A method of bivariate interpolation and smooth surface fitting for values given at irregularly distributed points. ACM TOMS 4(2)

  2. Alyuz N, Gokberk B, Spreeuwers L, Veldhuis R, Akarun L (2012) Robust 3D face recognition in the presence of realistic occlusions. 5thIAPR International Conference on Biometrics, New Delhi, pp 111–118

    Google Scholar 

  3. Amberg B, Knothe R, Vetter T (2008) Expression invariant 3D face recognition with a morphable model. 8th International Conference on Automatic Face & Gesture Recognition, Amsterdam, pp 1–6

    Google Scholar 

  4. Bhattacharjee D, Basu DK, Nasipuri M, Kundu M (2009) Human face recognition using fuzzy multilayer perceptron. Soft Comput 14(6)

  5. Bornak B, Arak I, Rafiei S, Sarikhani A, Babaei A (2010) 3D face recognition by used region-based with facial expression variation. 2ndInternational Conference on Signal Processing Systems, Dailan

    Book  Google Scholar 

  6. Cantzler H, Fisher RB (2001) Comparison of HK and SC curvature description methods. 3rd International Conference on 3-D Digital Imaging and Modeling, Quebec City, pp 285–291

    Google Scholar 

  7. Colombo A, Cusano C (2006) 3D face detection using curvature analysis. Pattern Recogn 39(3):444–455

    Article  MATH  Google Scholar 

  8. Creusot C, Pears N, Austin J (2013) A machine-learning approach to keypoint detection and landmarking on 3D meshes. Int J Comput Vis 102(1-3):146–179

    Article  Google Scholar 

  9. Drira H, Ben Amor B, Srivastava A, Daoudi M, Slama R (2013) 3D face recognition under expressions, occlusions and pose variations. IEEE Trans Pattern Anal Mach Intell 35(9):2270–2283

    Article  Google Scholar 

  10. Gordon GG (1991) Face recognition based on depth maps and surface curvature. SPIE Geometric methods in Computer Vision. pp 234–274

  11. Hajati F, Raie AA, Gao Y (2010) Pose-invariant 2.5D face recognition using geodesic texture warping. 1thInternational Conference on Control, Automation, Robotics and Vision, Singapore

    MATH  Google Scholar 

  12. Hajati F, Raie A, Gao Y (2011) 2.5D face recognition using patch geodesic moments. Pattern Recogn 45:969–982

    Article  MATH  Google Scholar 

  13. http://bosphorus.ee.boun.edu.tr/Content.aspx

  14. http://gavab.escet.urjc.es/recursos_en.html

  15. http://www.frav.es/databases/FRAV3d/

  16. https://software.intel.com/en-us/articles/realsense-overview

  17. Inan T, Halici U (2012) 3D face recognition using local shape descriptor. IEEE Trans Inf Forensic Secur 7(2):577–587

    Article  Google Scholar 

  18. Lee JT (1992) Evaluation of algorithms for surface interpolation over triangular patch. Inter-national Conference on International Society for Photography and Remote Sensing

  19. Li X, Zhang H (2007) Adapting geometric attributes for expression-invariant 3D face recognition. IEEE International Conference on Shape Modeling and Applications, Lyon, pp 21–32

    Google Scholar 

  20. Liu X, Sun C, Yang LT (2015) Multimedia Tools Appl 74(8):2803–2820

    Article  MathSciNet  Google Scholar 

  21. Lu X, Jain AK (2008) Deformation modeling for robust 3D face matching. IEEE Trans Pattern Anal Mach Intell 30(8):1346–1357

    Article  Google Scholar 

  22. Lu X, Jain AK, Colbry D (2006) Matching 2.5D face scans to 3D models. IEEE Trans Pattern Anal Mach Intell 28(1):31–43

    Article  Google Scholar 

  23. Mahoor MH, Abdel-Mottaleb M (2009) Face recognition based on 3D ridge images obtained from range data. Pattern Recogn 42(3):445–451

    Article  MATH  Google Scholar 

  24. Moreno A, Sanchez A, Velez J, Diaz F (2003) Face recognition using 3d surface-extracted descriptors. Proceedings of the Irish Machine Vision and Image Processing

  25. Moreno AB, Sanchez A, Velez JF, Diaz FJ (2003) Face recognition using 3d surface-extracted descriptors. Irish Machine Vision and Image Processing Conference

  26. Moreno AB, Sanchez A, Velez JF, Diaz FJ (2005) Face recognition using 3D local geometrical features: PCA vs. SVM. 4th International Symposium on Image and Signal Processing and Analysis. pp 185–190

  27. Mousavi MH, Faez K, Asghari A (2008) Three dimensional face recognition using SVM classifier. Seventh IEEE/ACIS International Conference on Computer and Information Science, Portland, pp 208–213

    Google Scholar 

  28. Mousavi MH, Faez K, Asghari A (2008) Three dimensional face recognition using SVM clas-sifier. Seventh IEEE/ACIS International Conference on Computer and Information Science pp. 208–213

  29. Passalis G, Perakis P, Theoharis T, Kakadiaris IA (2011) Using facial symmetry to handle pose variations in realworld 3d face recognition. IEEE Trans Pattern Anal Mach Intell 33(10)

  30. Perakis P, Passalis G, Theoharis T, Toderici G, Kakadiaris IA (2009) Partial matching of interpose 3D facial data for face recognition. 3rdInternational Conference on Biometrics: Theory, Applications, and Systems.IEEE, Washington

    Book  MATH  Google Scholar 

  31. Perakis P, Passalis G, Theoharis T, Kakadiaris IA (2010):3D facial landmark detection & faceregistrationA 3D facial landmark model & 3D local shape descriptors approach. In: TechReportTP-2010-01, Computer Graphics Laboratory, University of Athens

  32. Perakis P, Passalis G, Theoharis T, Kakadiaris IA (2013) 3D facial landmark detection under large yaw and expression variations. IEEE Trans Pattern Anal Mach Intell 35(7):1552–1564

    Article  Google Scholar 

  33. Salahshoor S, Faez K (2012) 3D face recognition using an expression insensitive dynamic mask. Image Signal Process 7340:253–260

    Article  Google Scholar 

  34. Shaiek A, Moutarde F (2011) 3D keypoints detection for objects recognition. International Conference on Image Processing, Computer vision and Pattern Recognition, Las Vegas

    Google Scholar 

  35. Shaiek A, Moutarde F (2012) Fast 3D keypoints detector and descriptor for view-based 3D objects recognition. Adv Depth Image Anal Appl 7854:106–115, Springer

    Article  Google Scholar 

  36. Sipiran I, Bustos B (2011) Harris 3D: a robust extension of the Harris operator for interest point detection on 3D meshes. Vis Comput 27(11):963–976

    Article  Google Scholar 

  37. Wang X, Ruan Q, Jin Y, Gaoyun A (2014) Three-dimensional face recognition under expression variation. EURASIP J Image Video Process 2014(1)

Download references

Acknowledgments

Authors are thankful for a project entitled “Development of 3D Face Recognition Techniques Based on Range Images,” supported by DeiTY, MCIT, Govt. of India, at the Department of Computer Science and Engineering, Jadavpur University, India for providing the necessary infrastructure to conduct experiments relating to this work.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, RCC Institute of Information Technology, Beliaghata, Kolkata, India

    Parama Bagchi

  2. Department of Computer Science and Engineering, Jadavpur University, Kolkata, India

    Debotosh Bhattacharjee & Mita Nasipuri

Authors
  1. Parama Bagchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Debotosh Bhattacharjee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mita Nasipuri
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Parama Bagchi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bagchi, P., Bhattacharjee, D. & Nasipuri, M. A robust analysis, detection and recognition of facial features in 2.5D images. Multimed Tools Appl 75, 11059–11096 (2016). https://doi.org/10.1007/s11042-015-2835-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-015-2835-7

Keywords

Search

Navigation