access icon free Face reconstruction from image sequences for forensic face comparison

The authors explore the possibilities of a dense model-free three-dimensional (3D) face reconstruction method, based on image sequences from a single camera, to improve the current state of forensic face comparison. They propose a new model-free 3D reconstruction method for faces, based on the Lambertian reflectance model to estimate the albedo and to refine the 3D shape of the face. This method avoids any form of bias towards face models and is therefore suitable in a forensic face comparison process. The proposed method can reconstruct frontal albedo images, from multiple non-frontal images. Also a dense 3D shape model of the face is reconstructed, which can be used to generate faces under pose. In the authors’ experiments, the proposed method is able to improve the face recognition scores in more than 90% of the cases. Using the likelihood ratio framework, they show for the same experiment that for data initially unsuitable for forensic use, the reconstructions become meaningful in a forensic context in more than 60% of the cases.

Inspec keywords: solid modelling; statistical analysis; image reconstruction; image sequences; image sensors; face recognition; image forensics

Other keywords: face recognition score improvement; 3D shape refining; likelihood ratio framework; image sequences; Lambertian reflectance model; dense 3D shape model; dense model-free 3D face reconstruction method; frontal albedo image reconstruction; forensic face comparison process; albedo estimation; multiple nonfrontal images

Subjects: Other topics in statistics; Image recognition; Computer vision and image processing techniques; Image sensors; Other topics in statistics; Graphics techniques

References

    1. 1)
      • 10. Marques, M., Costeira, J.: ‘3d face recognition from multiple images: A shape-from-motion approach’. FG, 2008, pp. 16.
    2. 2)
      • 15. Strecha, C., Fransens, R., Van Gool, L.: ‘Combined depth and outlier estimation in multiview stereo’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2006, 2006, vol. 2, pp. 23942401.
    3. 3)
      • 8. Fidaleo, D., Medioni, G.G.: ‘Model-assisted 3d face reconstruction from video’, in Zhou, S.K., Zhao, W., Tang, X., Gong, S. (Eds.): ‘AMFG’, ser. Lecture Notes in Computer Science (Springer, 2007), vol. 4778, pp. 124138.
    4. 4)
      • 19. Cognitec Systems GmbH: ‘FaceVACS SDK 8.8.0’, http://www.cognitec-systems.de, 2013.
    5. 5)
      • 21. Veldhuis, R.: ‘The relation between the secrecy rate of biometric template protection and biometric recognition performance’. Int. Conf. on Biometrics (ICB), 2015, 2015, vol. 5, pp. 311318.
    6. 6)
    7. 7)
    8. 8)
      • 3. Shan, Y., Liu, Z., Zhang, Z.: ‘Model-based bundle adjustment with application to face modeling’. IEEE Int. Conf. on Computer Vision, 2001, vol. 2, p. 644.
    9. 9)
      • 13. Hamsici, O.C., Gotardo, P.F.U., Martinez, A.M.: ‘Learning spatially-smooth mappings in non-rigid structure from motion’. Proc. of the 12th European Conf. on Computer Vision, ECCV'12, 2012, pp. 260273.
    10. 10)
      • 1. Blanz, V., Vetter, T.: ‘A morphable model for the synthesis of 3d faces’. Proc. of the 26th Annual Conf. on Computer Graphics and Interactive Techniques, 1999, pp. 187194.
    11. 11)
      • 12. Ishimoto, M., Chen, Y.-W.: ‘Pose-robust face recognition based on 3d shape reconstruction’. Fifth Int. Conf. on Natural Computation, 2009, ICNC'09, 2009, vol. 6, pp. 4043.
    12. 12)
      • 14. Spreeuwers, L.: ‘Multi-view passive 3d face acquisition device’. Proc. of the Special Interest Group on Biometrics and Electronic Signatures, ser. Lecture Notes in Informatics (LNI) – Proc., September 2008, vol. P-137, pp. 1324.
    13. 13)
      • 9. Park, U., Jain, A.K.: ‘3d model-based face recognition in video’, in Lee, S.-W., Li, S. (Eds.): ‘Advances in biometrics’, ser. Lecture Notes in Computer Science (Springer Berlin Heidelberg, 2007), vol. 4642, pp. 10851094.
    14. 14)
      • 20. Meuwly, D., Veldhuis, R.N.J.: ‘Biometrics – developments and potential’, in Allan, Jamieson, Andre, A. Moenssens (Eds.): ‘Wiley encyclopaedia of forensic science’ (John Wiley & Sons Ltd, Chichester, UK, 2014), vol. 1, pp. 18.
    15. 15)
      • 4. Roy-Chowdhury, A.K.: ‘3d face reconstruction from video using a generic model’. Int. Conf. on Multimedia and Expo, 2002, pp. 449452.
    16. 16)
    17. 17)
      • 7. Roy-Chowdhury, A.K., Chellappa, R., Gupta, H.: ‘3D face modeling from monocular video sequences’ (Academic Press, 2005), Ch. 6, pp. 185218.
    18. 18)
    19. 19)
      • 16. Garg, R., Roussos, A., Agapito, L.: ‘Dense variational reconstruction of non-rigid surfaces from monocular video’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2013, June 2013, pp. 12721279.
    20. 20)
      • 17. Delaunoy, A., Pollefeys, M.: ‘Photometric bundle adjustment for dense multi-view 3d modeling’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2014, June 2014, pp. 14861493.
    21. 21)
      • 18. van Dam, C., Spreeuwers, L., Veldhuis, R.: ‘Landmark-based model-free 3d face shape reconstruction from video sequences’. Proc. of the Int. Conf. of Biometrics Special Interest Group 2013 BIOSIG, September 2013, pp. 265272.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2015.0036
Loading

Related content

content/journals/10.1049/iet-bmt.2015.0036
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading