SIFT-based iris recognition revisited: prerequisites, advantages and improvements

  • C. Rathgeb
  • J. Wagner
  • C. Busch
Theoretical Advances


Scale-invariant feature transform (SIFT), which represents a general purpose image descriptor, has been extensively used in the field of biometric recognition. Focusing on iris biometrics, numerous SIFT-based schemes have been presented in past years, offering an alternative approach to traditional iris recognition, which are designed to extract discriminative binary feature vectors based on an analysis of pre-processed iris textures. However, the majority of proposed SIFT-based systems fails to maintain the recognition accuracy provided by generic schemes. Moreover, traditional systems outperform SIFT-based approaches with respect to other key system factors, i.e. authentication speed and storage requirement. In this work, we propose a SIFT-based iris recognition system, which circumvents the drawbacks of previous proposals. Prerequisites, derived from an analysis of the nature of iris biometric data, are utilized to construct an improved SIFT-based baseline iris recognition scheme, which operates on normalized enhanced iris textures obtained from near-infrared iris images. Subsequently, different binarization techniques are introduced and combined to obtain binary SIFT-based feature vectors from detected keypoints and their descriptors. On the CASIAv1, CASIAv4-Interval and BioSecure iris database, the proposed scheme maintains the performance of different traditional systems in terms of recognition accuracy as well as authentication speed. In addition, we show that SIFT-based features complement those extracted by traditional schemes, such that a multi-algorithm fusion at score level yields a significant gain in recognition accuracy.


Scale-invariant feature transform Biometrics Iris recognition 



Funding was partially provided by the German Federal Ministry of Education and Research (BMBF) as well as by the Hessen State Ministry for Higher Education, Research and the Arts (HMWK) within Center for Research in Security and Privacy (CRISP).


  1. 1.
    Alonso-Fernandez F, Tome-Gonzalez P, Ruiz-Albacete V, Ortega-Garcia J (2009) Iris recognition based on SIFT features. In: International conference on biometrics, identity and security (BIdS’09), pp 1–8Google Scholar
  2. 2.
    Baber J, Dailey MN, Satoh S, Afzulpurkar N, Bakhtyar M (2014) BIG-OH: binarization of gradient orientation histograms. Image Vis Comput 32(11):940–953CrossRefGoogle Scholar
  3. 3.
    Baber J, Dailey MN, Satoh S, Afzulpurkar N, Bakhtyar M (2014) Big-oh: BInarization of gradient orientation histograms. Image Vis Comput 32(11):940–953CrossRefGoogle Scholar
  4. 4.
    Bay H, Ess A, Tuytelaars T, Gool LV (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110(3):346–359CrossRefGoogle Scholar
  5. 5.
    Belcher C, Du Y (2009) Region-based SIFT approach to iris recognition. Opt Lasers Eng 47(1):139–147CrossRefGoogle Scholar
  6. 6.
    Bringer J, Despiegel V (2010) Binary feature vector fingerprint representation from minutiae vicinities. In: 4th IEEE International conference on biometrics: theory applications and systems (BTAS’10), pp 1–6Google Scholar
  7. 7.
    Burge MJ, Bowyer K (2016) Handbook of iris recognition, 2nd edn. Springer, New YorkGoogle Scholar
  8. 8.
    Calonder M, Lepetit V, Strecha C, Fua P (2010) BRIEF: binary robust independent elementary features. In: Proceedings of the 11th European conference on computer vision (ECCV’10), pp 778–792Google Scholar
  9. 9.
    Cappelli R, Ferrara M, Maltoni D (2010) Minutia cylinder-code: a new representation and matching technique for fingerprint recognition. IEEE Trans Pattern Anal Mach Intell 32(12):2128–2141CrossRefGoogle Scholar
  10. 10.
    Chen J, Shen F, Chen D, Flynn P (2016) Iris recognition based on human-interpretable features. IEEE Trans Inf Forensics Secur PP(99):1–10Google Scholar
  11. 11.
    Chen Y, Liu Y, Zhu X, He F, Wang H, Deng N (2014) Efficient iris recognition based on optimal subfeature selection and weighted subregion fusion. Sci World J 2014:1–19Google Scholar
  12. 12.
    Chinese Academy of Sciences’ Institute of Automation (2002) CASIA Iris Image Database V1.0.
  13. 13.
    Chinese Academy of Sciences’ Institute of Automation (2002) CASIA Iris Image Database V3.0.
  14. 14.
    Chinese Academy of Sciences’ Institute of Automation (2012) CASIA Iris Image Database V4.0.
  15. 15.
    Daugman J (1993) High confidence visual recognition of persons by a test of statistical independence. IEEE Trans Pattern Anal Mach Intell 15(11):1148–1161CrossRefGoogle Scholar
  16. 16.
    Daugman J (2004) How iris recognition works. IEEE Trans Circuits Syst Video Technol 14(1):21–30. CrossRefGoogle Scholar
  17. 17.
    Dong W, Sun Z, Tan T (2011) Iris matching based on personalized weight map. IEEE Trans Pattern Anal Mach Intell 33(9):1744–1757CrossRefGoogle Scholar
  18. 18.
    Fierrez J, Ortega-Garcia J, Toledano DT, Gonzalez-Rodriguez J (2007) Biosec baseline corpus: a multimodal biometric database. Pattern Recognit 40(4):1389–1392CrossRefzbMATHGoogle Scholar
  19. 19.
    Indian Institute of Technology Kanpur (2009) IITK Iris Image Database.
  20. 20.
    ISO/IEC JTC1 SC27 Security Techniques (2015) ISO/IEC 29794:2015. Information technology—biometric sample quality—part 6: iris image data. International Organization for StandardizationGoogle Scholar
  21. 21.
    ISO/IEC JTC1 SC27 Security Techniques (2016) ISO/IEC 30107-1:2016. Information technology—biometric presentation attack detection—part 1: framework. International Organization for StandardizationGoogle Scholar
  22. 22.
    ISO/IEC TC JTC1 SC37 Biometrics (2006) ISO/IEC 19795-1:2006. Information technology—biometric performance testing and reporting—part 1: principles and framework. International Organization for Standardization and International Electrotechnical CommitteeGoogle Scholar
  23. 23.
    Jain AK, Flynn P, Ross AA (2008) Handbook of biometrics. Springer, New YorkCrossRefGoogle Scholar
  24. 24.
    Jain AK, Klare B, Ross AA (2015) Guidelines for best practices in biometrics research. In: Proceedings of the 8th international conference on biometrics 2015 (ICB’15), pp 1–5Google Scholar
  25. 25.
    Jain AK, Ross A, Prabhakar S (2004) An introduction to biometric recognition. IEEE Trans Circuits Syst Video Technol 14:4–20. CrossRefGoogle Scholar
  26. 26.
    Kong AWK, Zhang D, Kamel MS (2010) An analysis of iriscode. IEEE Trans Image Process 19(2):522–532MathSciNetCrossRefGoogle Scholar
  27. 27.
    Krichen E, Mellakh MA, Garcia-Salicetti S, Dorizzi B (2004) Iris identification using wavelet packets. In: Proceedings of the 17th international conference on pattern recognition (ICPR’04), vol 4, pp 335–338Google Scholar
  28. 28.
    Li J, Lu Z (2011) B-SIFT: a highly efficient binary SIFT descriptor for invariant feature correspondence. In: Workshop on intelligent science and intelligent data engineering, pp 426–433Google Scholar
  29. 29.
    Li J, Lu Z (2012) Intelligent science and intelligent data engineering: second sino-foreign-interchange workshop, IScIDE 2011, chap. B-SIFT: a highly efficient binary SIFT descriptor for invariant feature correspondence, pp 426–433Google Scholar
  30. 30.
    Liu N, Zhang M, Li H, Sun Z, Tan T (2016) Deepiris: learning pairwise filter bank for heterogeneous iris verification. Pattern Recognit Lett 82:154–161 An insight on eye biometricsCrossRefGoogle Scholar
  31. 31.
    Liu X, Li P (2012) An iris recognition approach with SIFT descriptors. In: 7th International conference on advanced intelligent computing theories and applications. With aspects of artificial intelligence, pp 427–434Google Scholar
  32. 32.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  33. 33.
    Ma L, Tan T, Wang Y, Zhang D (2003) Personal identification based on iris texture analysis. IEEE Trans Pattern Anal Mach Intell 25(12):1519–1533CrossRefGoogle Scholar
  34. 34.
    Ma L, Tan T, Wang Y, Zhang D (2004) Efficient iris recognition by characterizing key local variations. IEEE Trans Image Process 13(6):739–750. CrossRefGoogle Scholar
  35. 35.
    Mansfield A, Wayman J (2002) Best practices in testing and reporting performance of biometric devices. Tech. rep., U.K. Goverment Biometrics Working GroupGoogle Scholar
  36. 36.
    Masek L (2003) Recognition of human iris patterns for biometric identification. Master’s thesis, University of Western AustraliaGoogle Scholar
  37. 37.
    Mehrotra H, Majhi B, Gupta P (2010) Robust iris indexing scheme using geometric hashing of SIFT keypoints. J Netw Comput Appl 33(3):300–313 Recent advances and future directions in biometrics personal identificationCrossRefGoogle Scholar
  38. 38.
    Mehrotra H, Majhi B, Sa P (2011) Unconstrained iris recognition using F-SIFT. In: 8th International conference on information, communications and signal processing (ICICS’11), pp 1–5Google Scholar
  39. 39.
    Monro DM, Rakshit S, Zhang D (2007) Dct-based iris recognition. IEEE Trans Pattern Anal Mach Intell 29(4):586–595CrossRefGoogle Scholar
  40. 40.
    Multimedia University (2004) MMU iris image database.
  41. 41.
    National Institute of Standards and Technology (NIST) (2005) Iris challenge evaluation (ICE).
  42. 42.
    Nguyen K, Fookes C, Ross A, Sridharan S (2017) Iris recognition with off-the-shelf cnn features: a deep learning perspective. IEEE Access PP(99):1–1Google Scholar
  43. 43.
    Nigam I, Vatsa M, Singh R (2015) Ocular biometrics: a survey of modalities and fusion approaches. Inf Fusion 26:1–35CrossRefGoogle Scholar
  44. 44.
    Ortega-Garcia J, Fierrez J, Alonso-Fernandez F, Galbally J, Freire MR, Gonzalez-Rodriguez J, Garcia-Mateo C, Alba-Castro JL, Gonzalez-Agulla E, Otero-Muras E, Garcia-Salicetti S, Allano L, Ly-Van B, Dorizzi B, Kittler J, Bourlai T, Poh N, Deravi F, Ng MW, Fairhurst M, Hennebert J, Humm A, Tistarelli M, Brodo L, Richiardi J, Drygajlo A, Ganster H, Sukno FM, Pavani SK, Frangi A, Akarun L, Savran A (2010) The multiscenario multienvironment biosecure multimodal database (BMDB). IEEE Trans Pattern Anal Mach Intell 32(6):1097–1111CrossRefGoogle Scholar
  45. 45.
    Park U, Pankanti S, Jain AK (2008) Fingerprint verification using sift featuresGoogle Scholar
  46. 46.
    Proença H, Alexandre LA (2005) Ubiris: a noisy iris image database. In: Proceedings of the 13th international conference on image analysis and processing (ICIAP’05), pp 970–977Google Scholar
  47. 47.
    Proença H, Filipe S, Santos R, Oliveira J, Alexandre L (2010) The UBIRIS.v2: a database of visible wavelength iris images captured on-the-move and at-a-distance. IEEE Trans Pattern Anal Mach Intell 32(8):1529–1535CrossRefGoogle Scholar
  48. 48.
    Raja KB, Raghavendra R, Stokkenes M, Busch C (2015) Multi-modal authentication system for smartphones using face, iris and periocular. In: Proceedings of the international conference on biometrics (ICB’15), pp 143–150Google Scholar
  49. 49.
    Sun Z, Tan T (2009) Ordinal measures for iris recognition. IEEE Trans Pattern Anal Mach Intell 31(12):2211–2226CrossRefGoogle Scholar
  50. 50.
    Sunder MS, Ross A (2010) Iris image retrieval based on macro-features. In: Proceedings of the 20th international conference on pattern recognition (ICPR’10), pp 1318–1321Google Scholar
  51. 51.
    Tomeo-Reyes I, Ross A, Clark A, Chandran V (2015) A biomechanical approach to iris normalization. In: International conference on biometrics (ICB’15), pp 9–16Google Scholar
  52. 52.
    USIT (2016) University of Salzburg iris toolkit. Version 2.0
  53. 53.
    University of Bath (2004) University of Bath iris image database.
  54. 54.
    Vandewalle P, Kovacevic J, Vetterli M (2009) Reproducible research in signal processing—what, why, and how. IEEE Signal Process Mag 26(3):37–47CrossRefGoogle Scholar
  55. 55.
    West Virgina University (2005) WVU iris image database.
  56. 56.
    Yang G, Pang S, Yin Y, Li Y, Li X (2012) SIFT based iris recognition with normalization and enhancement. Int J Mach Learn Cybern 4(4):401–407CrossRefGoogle Scholar
  57. 57.
    Yu L, Zhang D, Wang K (2007) The relative distance of key point based iris recognition. Elsevier Pattern Recognit 40(2):423–430CrossRefzbMATHGoogle Scholar
  58. 58.
    Zhu R, Yang J, Wu R (2006) Iris recognition based on local feature point matching. In: International symposium on communications and information technologies (ISCIT’06), pp 451–454Google Scholar
  59. 59.
    Zuiderveld K (1994) Graphics gems iv. chap. Contrast limited adaptive histogram equalization, pp 474–485Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.da/sec - Biometrics and Internet Security Research Group Hochschule DarmstadtDarmstadtGermany

Personalised recommendations