access icon free Hybrid robust iris recognition approach using iris image pre-processing, two-dimensional gabor features and multi-layer perceptron neural network/PSO

Computational intelligence is employed to solve factual and complicated global problems, though neural networks (NNs) and evolutionary computing have also affected these issues. Biometric traits are applicable for detecting crime in security systems because they offer attractive features such as stability and uniqueness. Although various methods have been proposed for this objective, feature shortcomings such as computational complexity, long run times, and high memory consumption remain. The current study proposes a novel human iris recognition approach based on a multi-layer perceptron NN and particle swarm optimisation (PSO) algorithms to train the network in order to increase generalisation performance. A combination of these algorithms was used as a classifier. A pre-processing step was performed on the iris images to improve the results and two-dimensional gabor kernel feature extraction was applied. The data was normalised, trained, and tested using the proposed method. A PSO algorithm was applied to train the NN for data classification. The experimental results show that the proposed method performs better than many other well-known techniques. The benchmark Chinese Academy of Science and Institute of Automation (CASIA)-iris V3 and Center for Machine Learning and Intelligent Systems at the University of California, Irvine (UCI) machine learning repository datasets were used for testing and comparison.

Inspec keywords: iris recognition; particle swarm optimisation; learning (artificial intelligence); computational complexity; neural nets; feature extraction

Other keywords: 2D Gabor kernel feature extraction; data classification; iris image pre-processing; PSO algorithms; 2D Gabor features; evolutionary computing; complicated global problems; security systems; neural networks; hybrid robust iris recognition; multilayer perceptron neural network/PSO; human iris recognition; multilayer perceptron NN; generalisation performance; computational intelligence; biometric traits; particle swarm optimisation; computational complexity; UCI machine learning repository datasets

Subjects: Data handling techniques; Optimisation techniques; Computational complexity; Optimisation techniques; Computer vision and image processing techniques; Knowledge engineering techniques; Image recognition

References

    1. 1)
      • 35. Wildes, R.P., Asmuth, J.C., Green, G.L.: ‘A machine-vision system for iris recognition’, Mach. Vis. Appl., 1996, 9, (1), pp. 18.
    2. 2)
      • 25. Nedjah, N., da Silva, R.M., de Macedo Mourelle, L.: ‘Compact yet efficient hardware implementation of artificial neural networks with customized topology’, Expert Syst. Appl., 2012, 39, (10), pp. 91919206.
    3. 3)
      • 45. Yiqing, L., Xigang, Y., Yongjian, L.: ‘An improved PSO algorithm for solving non-convex NLP/MINLP problems with equality constraints’, Comput. Chem. Eng., 2007, 31, (3), pp. 153162.
    4. 4)
      • 50. Ali, H., Salami, M.-J.E.: ‘Iris recognition system using support vector machine’. Int. Conf. Computer and Communication Eng., 2008, pp. 516521.
    5. 5)
      • 37. Daugman, J.: ‘High confidence recognition of persons by rapid video analysis of iris texture’. IET European Convention on Security and Detection, 1995, pp. 244251.
    6. 6)
      • 21. Raghu, P.P., Yegnanarayana, B.: ‘Segmentation of gabor-filtered textures using deterministic relaxation’, IEEE Trans. Image Process., 1996, 5, (12), pp. 16251636.
    7. 7)
      • 36. Ahmadi, N., Akbarizadeh, G.: ‘Iris recognition system based on canny and LoG edge detection methods’, J. Soft Comput. Decis. Support Syst., 2015, 2, (4), pp. 2630.
    8. 8)
      • 26. Kennedy, J., Eberhart, R.C.: ‘A discrete binary version of the particle swarm algorithm’, IEEE Int. Conf. Syst. Man Cybern. Comput. Cybern. Simul., 1997, 5, pp. 41044108.
    9. 9)
      • 28. Pan, Q.K., Tasgetiren, M.F., Liang, Y.C.: ‘A discrete particle swarm optimization algorithm for the no-wait flow shop scheduling problem’, Comput. Oper. Res., 2008, 35, (9), pp. 28072839.
    10. 10)
      • 2. Delac, K., Grgic, M.: ‘A survey of biometric recognition methods’. 46th IEEE Int. Proc. Symp. Electronics and Marine, 2004, pp. 184193.
    11. 11)
      • 51. Gaxiola, F., Melin, P., Valdez, F.: ‘Neural network with type-2 fuzzy weights adjustment for pattern recognition of the human iris biometrics’. Advances in Computational Intelligent, 2012, pp. 259270.
    12. 12)
      • 19. Shaikh, N.F., Doye, D.D.: ‘An adaptive central force optimization (ACFO) and feed forward back propagation neural network (FFBNN) based iris recognition system’, J. Intell. Fuzzy Syst., 2016, 30, (4), pp. 20832094.
    13. 13)
      • 5. Ahmadi, N., Akbarizadeh, G.: ‘A review of iris recognition based on biometric technologies’, Transylvanian Rev., 2016, 24, (4), pp. 151163.
    14. 14)
      • 39. Naotoshi, S.: ‘Texture segmentation using gabor filters ENEE731 project 1’, 2006.
    15. 15)
      • 24. Farouk, R.M., Kumar, R., Riad, K.A.: ‘Iris matching using multi-dimensional artificial neural network’, IET Comput. Vis., 2011, 5, (3), pp. 178184.
    16. 16)
      • 53. Dias, U., Frietas, V., Sandeep, P.S.: ‘A neural network based iris recognition system for personal identification’, ICTACT J. Soft Comput., 2010, 1, (2), pp. 7884.
    17. 17)
      • 27. Clerc, M.: ‘Discrete particle swarm optimization, illustrated by the traveling salesman problem’, New optimization techniques in engineering (Springer, Berlin Heidelberg, 2004), pp. 219239.
    18. 18)
      • 30. Ahonen, T., Hadid, A., Pietikainen, M.: ‘Face description with local binary patterns: application to face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (12), pp. 20372041.
    19. 19)
      • 29. Eberhart, R.C., Kennedy, J.: ‘A new optimizer using particle swarm theory’. Proc. Sixth Int. Symp. Micro Machine and Human Science, 1995, vol. 1, pp. 3943.
    20. 20)
      • 40. Wade, J.J., McDaid, L.J., Santos, J.A.: ‘SWAT: a spiking neural network training algorithm for classification problems’, IEEE Trans. Neural Netw., 2010, 21, (11), pp. 18171830.
    21. 21)
      • 48. Murphy, P.M., Aha, D.W.: ‘UCI repository of machine learning databases’. Available at http://www.ics.uci.edu/∼mlearn/MLRepository.html, Irvine, CA: the University of California, Department of Information and Computer Science, accessed 15 June 2016.
    22. 22)
      • 43. Welhazi, Y., Guesmi, T., Abdallah, H.H.: ‘Eigenvalue assignments in multi machine power systems using multi-objective PSO algorithm’, Int. J. Energy Optim. Eng. (IJEOE), 2015, 4, (3), pp. 3348.
    23. 23)
      • 15. Chen, C.H., Chu, C.T.: ‘High performance iris recognition based on 1-D circular feature extraction and PSO–PNN classifier’, Expert Syst. Appl., 2009, 36, (7), pp. 1035110356.
    24. 24)
      • 7. Tallapragada, V.S., Rajan, E.G.: ‘Morphology based non-ideal iris recognition using decision tree classifier’. IEEE Int. Conf. Pervasive Computing (ICPC), 2015, pp. 14.
    25. 25)
      • 13. Ma, Z., Qi, M., Kang, : ‘Iris verification using wavelet moments and neural network’. Int. Conf. Life System Modeling and Simulation, 2007, pp. 218226.
    26. 26)
      • 33. Pare, D.F.Jr., Hoffman, N., Lee, J.A.: U.S. Patent No. 6,154,879, U.S. Patent and Trademark Office, Washington, DC, 2008.
    27. 27)
      • 49. Rai, H., Yadav, A.: ‘Iris recognition using combined support vector machine and Hamming distance approach’, Expert Syst. Appl., 2014, 41, (2), pp. 588593.
    28. 28)
      • 3. Jain, A.K., Ross, A., Pankanti, S.: ‘Biometrics: a tool for information security’, IEEE Trans. Inf. Forensics Sec., 2006, 1, (2), pp. 125143.
    29. 29)
      • 44. van der Merwe, D.W., Engelbrecht, A.P.: ‘Data clustering using particle swarm optimization’. IEEE Congress on Evolutionary Computation, 2003, vol. 1, pp. 215220.
    30. 30)
      • 52. Raja, V.S., Rajagopalan, S.P.: ‘IRIS recognition system using neural network and genetic algorithm’, Int. J. Comput. Appl., 2013, 68, (20), pp. 4953.
    31. 31)
      • 1. Tisse, C.L., Martin, L., Torres, L., et al: ‘Person identification technique using human iris recognition’. Proc. Vision Interface, 2002, pp. 294299.
    32. 32)
      • 10. Cho, S., Kim, J.: ‘Iris recognition using LVQ neural network’. Int. Symp. Neural Networks, 2006, pp. 2633.
    33. 33)
      • 47. ‘Database of human iris. Institute of Automation of Chinese Academy of Sciences (CASIA)’. Available at http://www.cbsr.ia.ac.cn/english/IrisDatabase.asp, accessed 26 July 2016.
    34. 34)
      • 31. Carafano, J.J.: ‘The future of anti-terrorism technologies’ (Heritage Foundation, 2005).
    35. 35)
      • 23. Wang, A., Chen, Y., Zhang, X.: ‘Iris recognition based on 2D wavelet and AdaBoost neural network’. Trends in Intelligent Systems and Computer Engineering, 2008, pp. 117128.
    36. 36)
      • 17. Chen, C.H., Chu, C.T.: ‘Low complexity iris recognition based on wavelet probabilistic neural networks’. Proc. 2005 IEEE Int. Joint Conf. Neural Networks, 2005, vol. 3, pp. 19301935.
    37. 37)
      • 18. Tsai, C.C., Taur, J.S., Tao, C.W.: ‘Iris recognition using gabor filters optimized by the particle swarm technique’. IEEE Int. Conf. Man and Cybernetics in Systems, 2008, pp. 921926.
    38. 38)
      • 46. Liu, C., Wechsler, H.: ‘Independent component analysis of gabor features for face recognition’, IEEE Trans. Neural Netw., 2003, 4, (4), pp. 919928.
    39. 39)
      • 41. Dahmani, K., Notton, G., Voyant, C.: ‘Multilayer perceptron approach for estimating 5 min and hourly horizontal global irradiation from exogenous meteorological data in locations without solar measurements’, Renew. Energy, 2016, 90, pp. 267282.
    40. 40)
      • 32. Al-Raisi, A.N., Al-Khouri, A.M: ‘Iris recognition and the challenge of homeland and border control security in UAE’, Telemat. Inform., 2008, 25, (2), pp. 117132.
    41. 41)
      • 12. Ye, X., Yao, P., Long, F.: ‘Iris image real-time pre-estimation using compound BP neural network’. Int. Conf. Biometrics, 2006, pp. 450456.
    42. 42)
      • 11. Srivastava, V., Tripathi, B.K., Pathak, V.K.: ‘Biometric recognition by hybridization of evolutionary fuzzy clustering with functional neural networks’, J. Ambient Int. Humanized Comput., 2014, 5, (4), pp. 525537.
    43. 43)
      • 14. Dhage, S.S., Hegde, S.S., Manikantan, K.: ‘DWT-based feature extraction and radon transform based contrast enhancement for improved iris recognition’, Proc. Comput. Sci., 2015, 45, pp. 256265.
    44. 44)
      • 42. Kolehmainen, M., Martikainen, H., Ruuskanen, J.: ‘Neural networks and periodic components used in air quality forecasting’, Atmos. Environ., 2001, 35, (5), pp. 815825.
    45. 45)
      • 6. Alheeti, K.M.A.: ‘Biometric iris recognition based on hybrid technique’, Int. J. Soft Comput., 2011, 2, (4), p. 1.
    46. 46)
      • 22. Gaxiola, F., Melin, P., Valdez, F.: ‘Modular neural networks with type-2 fuzzy integration for pattern recognition of iris biometric measure’. Advances in Soft Computing, 2011, pp. 363373.
    47. 47)
      • 4. Yan, S., Xu, D., Zhang, B.: ‘Graph embedding and extensions: a general framework for dimensionality reduction’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (1), pp. 4051.
    48. 48)
      • 9. Abiyev, R.H., Altunkaya, K.: ‘Neural network based biometric personal identification with fast iris segmentation’, Int. J. Control Autom. Syst., 2009, 7, (1), pp. 1723.
    49. 49)
      • 55. Daugman, J.: ‘High confidence visual recognition of person by a test of statistical independence’, IEEE Trans. Pattern Anal. Mach. Intell., 1993, 15, (11), pp. 11481151.
    50. 50)
      • 38. Jain, A.K., Farrokhnia, F.: ‘Unsupervised texture segmentation using gabor filters’. IEEE Int. Conf. System, Man and Cybernetics, Conf. Proc., 1990, pp. 1419.
    51. 51)
      • 54. Ma, L., Wang, Y., Tan, T.: ‘Iris recognition based on multichannel gabor filtering’. Proc. Fifth Asian Conf. Computer Vision, 2002, pp. 279283.
    52. 52)
      • 34. Eliza Du, Y.: ‘Review of iris recognition: cameras, systems, and their applications’, Sens. Rev., 2006, 26, (1), pp. 6669.
    53. 53)
      • 8. Daugman, J.G.: U.S. Patent No. 5,291,560, U.S. Patent and Trademark Office, Washington, DC, 1994.
    54. 54)
      • 20. Clausi, D.A., Jernigan, M.E.: ‘Designing gabor filters for optimal texture separability’, Pattern Recognit., 2000, 33, (11), pp. 18351849.
    55. 55)
      • 16. Hollingsworth, K., Bowyer, K.W., Flynn, P.J.: ‘Pupil dilation degrades iris biometric performance’, Comput. Vis. Image Underst., 2009, 113, (1), pp. 150157.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2017.0041
Loading

Related content

content/journals/10.1049/iet-bmt.2017.0041
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading