Best Practices in Reporting Iris Recognition Results

  • Nicolaie Popescu-Bodorin
  • Valentina E. Balas
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 357)


This article discusses old and new ways of estimating the performance of an actual or simulated iris recognition system, old and new manners of comparing different actual or simulated iris recognition systems in terms of security and comfort, and makes some considerations on choosing and comparing the processing methods engaged as subtasks of iris recognition. Along the discussion, from time to time, the article summarizes and points out to the open problems and to the best practices on a given topic, selected strictly on a logical basis, regardless if the practices under discussion are popular or not today, regardless the degree of consensus explicitly or implicitly expressed in the current community and literature of the field on the topics at hand.



This work was partially supported by the University of South-East Europe Lumina (Bucharest, Romania), Lumina Foundation (Bucharest, Romania), and Intelligent Systems Laboratory (Aurel Vlaicu University of Arad, Romania).


  1. 1.
    Cross-Sensor Comparison Competition 2013.
  2. 2.
  3. 3.
    Daugman JG (1993) High confidence visual recognition of persons by a test of statistical independence. IEEE Trans Pattern Anal Mach Intell 15(11):1148–1161. doi: 10.1109/34.244676
  4. 4.
    Daugman JG (2000) Biometric decision landscapes, Technical Report TR482, University of Cambridge, Computer LaboratoryGoogle Scholar
  5. 5.
    Daugman JG, Downing C (2001) Epigenetic randomness, complexity, and singularity of human iris patterns. Proc Royal Soc B Biological Sciences 268:1737–1740. doi: 10.1098/rspb.2001.1696
  6. 6.
    Daugman JG (2001) Statistical richness of visual phase information: update on recognition persons by iris patterns. Int. J. Comput Vis 45(1):25–38zbMATHCrossRefGoogle Scholar
  7. 7.
    Daugman JG (2003) Demodulation by complex-valued wavelets for stochastic pattern recognition. Int J Wavelets Multiresolut Inf Process 1(1):1–17. doi: 10.1142/S0219691303000025 zbMATHCrossRefGoogle Scholar
  8. 8.
    Daugman JG (2003) The importance of being random: statistical principles of iris recognition. Pattern Recogn 36:279–291. doi: 10.1016/S0031-3203(02)00030-4 CrossRefGoogle Scholar
  9. 9.
    Balas VE, Noaica CM, Popa JR, Munteanu C, Stroescu VC (2014) Establishing PNN-based iris code to identity fuzzy membership for consistent enrollment. In: Proceedings of 6th IEEE international conference on soft computing and applications, Timisoara, Romania, 24–26 July 2014Google Scholar
  10. 10.
    Popescu-Bodorin N, Balas VE (2012) Learning Iris biometric digital identities for secure authentication-a neural-evolutionary perspective pioneering intelligent iris identification. In: Recent advances in intelligent engineering systems, Springer, Berlin, pp 409–434. doi: 10.1007/978-3-642-23229-9_19
  11. 11.
    Popescu-Bodorin N, Balas VE (2011) Exploratory simulation of an intelligent iris verifier distributed system. In: Proceedings of 6th IEEE international symposium on applied computational intelligence, IEEE Press, pp 259–262. ISBN 978-1-4244-9108-7Google Scholar
  12. 12.
    Popescu-Bodorin N, Balas VE, Motoc IM (2011) Iris codes classification using discriminant and witness directions. In: Proceedings of 5th IEEE international symposium on computational intelligence and intelligent informatics, IEEE Press, Floriana, Malta, 15–17 Sept, pp 143–148. doi: 10.1109/ISCIII.2011.6069760
  13. 13.
    Popescu-Bodorin N, Balas VE (2014) Fuzzy Membership, possibility, probability and negation in biometrics. Acta Polytech Hung 11(50), No. 4/2014:79–100Google Scholar
  14. 14.
    Turing AM (1950) Computing machinery and intelligence. Mind 59:433–460MathSciNetCrossRefGoogle Scholar
  15. 15.
    Balas VE, Motoc IM, Barbulescu A (2013) Combined Haar-Hilbert and Log-Gabor based iris encoders, Studies in computational intelligence, New concepts and applications in soft computing, vol 417. Springer, Heidelberg, pp 1–26. doi: 10.1007/978-3-642-28959-0_1
  16. 16.
    Proença H, Alexandre LA (2007) Iris recognition-A method to increase the robustness to noisy Imaging environments through the selection of the higher discriminating features. In: International conference on computational intelligence and multimedia applications, vol 3. IEEE, pp 301–307. doi: 10.1109/ICCIMA.2007.119
  17. 17.
    Krichen E, Chenafa M, Garcia-Salicetti S, Dorizzi B (2007) Color-based iris verification. In: advances in biometrics, Springer, Berlin, pp. 997–1005. doi: 10.1007/978-3-540-74549-5_104
  18. 18.
    Radu P, Sirlantzis K, Howells WGJ, Deravi F, Hoque S (2011) Information fusion for unconstrained iris recognition. Int J Hybrid Inf Technol 4(4)Google Scholar
  19. 19.
    Ayer AJ (1936) Language, truth, and logic. Victor Gollanez Ltd., LondonGoogle Scholar
  20. 20.
    Matheny AP, Dolan AB (1975) Changes in eye colour during early childhood-sex and genetic differences. Ann Hum Biol 2(2):191–196CrossRefGoogle Scholar
  21. 21.
    Bito LZ (2001) A new approach to the medical management of glaucoma, from the bench to the clinic, and beyond-the Proctor Lecture. Invest Ophthalmol Vis Sci 42(6):1126–1133Google Scholar
  22. 22.
    Bito LZ, Matheny A, Cruickshanks KJ, Nondahl DM, Carino OB (1997) Eye color changes past early childhood-the louisville twin study. Arch Ophthalmol 115(5):659–663CrossRefGoogle Scholar
  23. 23.
  24. 24.
    Popescu-Bodorin N, Balas VE, Motoc IM (2013) The biometric menagerie—a fuzzy and inconsistent concept, Soft computing applications. Adv Intell Syst Comput 195:27–43. doi: 10.1007/978-3-642-33941-7_6 Springer VerlagCrossRefGoogle Scholar
  25. 25.
    Motoc IM, Noaica CM, Badea R, Ghica CG (2013) Noise influence on the fuzzy-linguistic partitioning of iris code space, Soft computing applications. Adv Intell Syst Comput 195:71–82. doi: 10.1007/978-3-642-33941-7_9 CrossRefGoogle Scholar
  26. 26.
    Popescu-Bodorin N, Lucian G, Balas VE, Munteanu C, Manu I, Herea A, Stroescu V (2013) Cross-Sensor Comparison-LG4000-to-LG2200. Technical Report 460/24-07-2013, Rev. No. 4/30-09-2013, University of South-East Europe Lumina, Bucharest, RomaniaGoogle Scholar
  27. 27.
    Mansfield AJ, Wayman JL (2002) Best practices in testing and reporting performance of biometric devices. Middlesex, UK-Centre for Mathematics and Scientific Computing, National Physical Laboratory, Teddington, pp 1–36Google Scholar
  28. 28.
    Quinn GW, Grother P, Ngan M (2013) IREX IV: part 1, evaluation of iris identification algorithms. NIST Interagency Report 7949, Information Access Division, National Institute of Standards and TechnologyGoogle Scholar
  29. 29.
    Popescu-Bodorin N, Balas VE (2010) Comparing Haar-Hilbert and Log-Gabor based iris encoders on bath iris image database. In: Proceedings 4th International Workshop on soft computing applications, IEEE Press, pp 191–196. doi: 10.1109/SOFA.2010.5565599
  30. 30.
    CASIA Iris Image Database.

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Nicolaie Popescu-Bodorin
    • 1
    • 2
  • Valentina E. Balas
    • 3
    • 4
  1. 1.University of S-E Europe LuminaBucharestRomania
  2. 2.Head of Applied Computer Science Testing LaboratoryBucharestRomania
  3. 3.University ‘Aurel Vlaicu’ of AradAradRomania
  4. 4.Head of Intelligent Systems LaboratoryAradRomania

Personalised recommendations