access icon free Personal identification from degraded and incomplete high resolution palmprints

A high resolution palmprint recognition system using full or partial, eventually degraded, palmprints is presented. Previous work on palmprint matching addressed mostly commercial applications, using low resolution images. However, in forensic scenarios, high resolution palmprints, although incomplete and/or degraded, are often used. Degradations may result from surface irregularities or impurities, which are often modelled as Gaussian or salt and pepper noise, as well as smearing of the palmprint because of hand sliding, which in this work is modelled as motion blur. The proposed system matches palmprints, full or partial, undegraded or subjected to one of the above degradations, against palmprints registered in a database. The proposed system extends previous work of the authors by adaptively selecting between two palmprint matching approaches, achieving better recognition results than either of the two individual strategies. The first approach relies on a motion blur compensation technique, while the second is based on a combination of the Fourier–Mellin transform with a modified phase-only correlation matching strategy. The presented results show that for sufficiently large palmprint areas the blur compensation technique works better, while for small-sized partial palmprints with large motion blur degradation values the second approach based on correlation is preferred.

Inspec keywords: motion compensation; image resolution; Gaussian noise; palmprint recognition; Fourier transforms; image forensics; image matching

Other keywords: surface irregularity; forensic; personal identification; palmprint matching; palmprint recognition system; Gaussian noise; salt and pepper noise; Fourier–Mellin transform; phase-only correlation matching strategy; motion blur compensation technique

Subjects: Integral transforms; Computer vision and image processing techniques; Other topics in statistics; Other topics in statistics; Image recognition; Integral transforms

References

    1. 1)
      • 10. THUPALMLAB’, http://ivg.au.tsinghua.edu.cn/index.php?n=Data.Tsinghua500ppi, accessed July 2013.
    2. 2)
    3. 3)
      • 16. VLFeat toolkit’, http://www.vlfeat.org/index.html, accessed February 2013.
    4. 4)
    5. 5)
      • 17. Gonzalez, R.C., Woods, R.E.: ‘Regional descriptors’, in ‘Digital image processing’ (Prentice Hall, Upper Saddle River, NJ, 2007, 3rd edn.), pp. 849861.
    6. 6)
      • 9. Brusius, F., Schwanecke, U., Barth, P.: ‘Blind image deconvolution of linear motion blur’, in Csurka, G., et al (Eds.): ‘VISIGRAPP 2011, CCIS 274’ (Springer, 2013, 1st edn.), pp. 105119.
    7. 7)
      • 7. Carreira, L., Correia, P.L., Soares, L.D.: ‘On high resolution palmprint matching’. Int. Workshop Biometrics Forensics, Valletta, Malta, March 2014, pp. 16.
    8. 8)
    9. 9)
      • 15. Juan, L., Gwun, O.: ‘A comparison of SIFT, PCA-SIFT and SURF’, Int. J. Image Process., 2009, 3, (4), pp. 143152.
    10. 10)
      • 13. Gonzalez, R.C., Woods, R.E.: ‘Image restoration and reconstruction’, in ‘Digital image processing’ (Prentice Hall, Upper Saddle River, NJ, 2007, 3rd edn.), pp. 352357.
    11. 11)
      • 8. Singh, S., Correia, P.L., Soares, L.D.: ‘Improved rotation-invariant degraded partial palmprint recognition technique’. European Signal Processing Conf., Bucharest, Romania, August 2012, pp. 14991503.
    12. 12)
      • 20. SourceAFIS’, http://www.sourceafis.org/blog/, accessed January 2015.
    13. 13)
    14. 14)
      • 11. PV-TEST’, https://biolab.csr.unibo.it/fvcongoing/UI/Form/Home.aspx, accessed March 2012.
    15. 15)
      • 3. Laadjel, M., Kurugollu, F., Bouridane, A., Boussakta, S.: ‘Degraded partial palmprint recognition for forensic investigations’. Int. Conf. Image Processing, Cairo, Egypt, November 2009, pp. 15131516.
    16. 16)
    17. 17)
      • 5. Wang, R., Ramos, D., Fierrez, J., Krish, R.P.: ‘Towards regional fusion for high-resolution palmprint recognition’. Conf. Graphics, Patterns Images, Arequipa, Peru, August 2013, pp. 357361.
    18. 18)
    19. 19)
      • 14. Steerable-filter’, https://github.com/andreydung/Steerable-filter, accessed February 2013.
    20. 20)
      • 1. On latent palmprint matching’, http://www.cse.msu.edu/biometrics/Publications/Palmprints/JainDemirkusOnLatentPalmprintMatching08.pdf, accessed January 2015.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2014.0043
Loading

Related content

content/journals/10.1049/iet-bmt.2014.0043
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading