{"title":"Efficient Feature Fusion for Noise Iris in Unconstrained Environment","authors":"Yao-Hong Tsai","volume":97,"journal":"International Journal of Computer and Information Engineering","pagesStart":329,"pagesEnd":333,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10000671","abstract":"
This paper presents an efficient fusion algorithm for
\r\niris images to generate stable feature for recognition in unconstrained
\r\nenvironment. Recently, iris recognition systems are focused on real
\r\nscenarios in our daily life without the subject’s cooperation. Under
\r\nlarge variation in the environment, the objective of this paper is to
\r\ncombine information from multiple images of the same iris. The
\r\nresult of image fusion is a new image which is more stable for further
\r\niris recognition than each original noise iris image. A wavelet-based
\r\napproach for multi-resolution image fusion is applied in the fusion
\r\nprocess. The detection of the iris image is based on Adaboost
\r\nalgorithm and then local binary pattern (LBP) histogram is then
\r\napplied to texture classification with the weighting scheme.
\r\nExperiment showed that the generated features from the proposed
\r\nfusion algorithm can improve the performance for verification system
\r\nthrough iris recognition.<\/p>\r\n","references":"[1] J. G. Daugman, \u201cHigh confidence visual recognition of persons by a test\r\nof statistical independence,\u201d IEEE Trans. Pattern Anal. Machine Int.,\r\nvol. 15, no. 11, 1993, pp. 1148\u20131161.\r\n[2] J. G. Daugman, \u201cHow iris recognition works,\u201d IEEE Trans. Circuits\r\nSystems Video Technol., vol. 14, no. 1, 2004, pp. 21\u201329.\r\n[3] P. W. Hallinan, \u201cRecognizing human eyes,\u201d Geometric Methods in\r\nComputer Vision, vol. 1570, pp. 214\u2013226, 1991.\r\n[4] K. W. Bowyer, K. Hollingsworth, P.J. Flynn, Image understanding for\r\niris biometrics: a survey, Computer Vision Image Understanding, vol.\r\n110, no. 2, 2008.\r\n[5] H. Proen\u00e7a, S. Filipe, R. Santos, J. Oliveira, and L. A. Alexandre, \u201cThe\r\nUBIRIS.v2: A database of visible wavelength iris images captured onthe-\r\nmove and at-adistance,\u201d IEEE Trans. Pattern Anal. Machine Intell.,\r\nvol. 32, 2010, pp. 1529\u20131535.\r\n[6] J. Daugman, \u201cNew methods in iris recognition,\u201d IEEE Trans. Systems,\r\nMan, Cybernet., Part B vol. 37, 2007, pp. 1167\u20131175.\r\n[7] Z. Sun and T. Tan, \u201cOrdinal measures for iris recognition,\u201d IEEE Trans.\r\nPattern Anal. Machine Intell., vol. 31, 2009, pp. 2211\u20132226.\r\n[8] P. Li and H. Ma, \u201cIris recognition in non-ideal imaging conditions,\u201d\r\nPattern Recognition Letters, vol. 33, no. 8, 2012, pp. 1012\u20131018.\r\n[9] H. Proen\u00e7a, L.A. Alexandre, Iris segmentation methodology for\r\nnoncooperative recognition, IEEE Proceedings of the Vision, Image and\r\nSignal Processing, vol. 153, no. 2, 2006, pp. 199\u2013205.\r\n[10] J. G. Daugman, New methods in iris recognition, IEEE Transactions on\r\nSystem, Man, and Cybernetics\u2013Part B: Cybernetics, vol. 37, no. 5, 2007,\r\npp. 1167\u20131175.\r\n[11] K. W. Bowyer, K. Hollingsworth, and P. J. Flynn, \u201cImage understanding\r\nfor iris biometrics: A survey,\u201d Computer Vision and Image\r\nUnderstanding, vol. 110, 2008, pp. 281\u2013307.\r\n[12] H. Proen\u00e7a, L.A. Alexandre, The NICE.I: noisy iris challenge evaluation\r\n\u2013 part I, in: Proceedings of the of First International Conference on\r\nBiometrics: Theory, Applications, and Systems, 2007, pp. 1\u20134.\r\n[13] H. Proen\u00e7a, S. Filipe, R. Santos, J. Oliveira, and L. A. Alexandre, \u201cThe\r\nUBIRIS.v2: A database of visible wavelength iris images captured onthe-\r\nmove and at-a-distance,\u201d IEEE Trans. Pattern Anal. Machine Intell.,\r\nvol. 32, 2010, pp. 1529\u20131535.\r\n[14] Y. H. Tsai, \u201cA Weighted Approach to Unconstrained Iris Recognition,\u201d\r\nin Proc. International Conference on Computer Science and Intelligent\r\nSystems, London, UK, 2014.\r\n[15] Iris image database. http:\/\/socia-lab.di.ubi.pt\/\r\n[16] Y. Moses, S. Edelman, and S. Ullamn, \u201cGeneralization on Novel Images\r\nin Upright and Inverted Faces,\u201d Perception, vol. 25, 1996, pp. 443-461.\r\n[17] P. J. Phillips and Y. Vardi, \u201cEfficient Illumination Normalization of\r\nFacial Images,\u201d Pattern Recognition Letters, vol. 17, 1996, pp. 921-927.\r\n[18] P. Viola, M. J. Jonse, \u201cRobust Real-Time Face Detection,\u201d International\r\nJournal of Computer Vision, vol. 57, no. 2, 2004, pp. 137-154.\r\n[19] Y. Freund and R. E. Schapire, \u201cExperiments with a New Boosting\r\nAalgorithm,\u201d in Proc. 13th International Conference on Machine\r\nLearning, Bari, Italy, 1996, pp. 148-156.\r\n[20] R. E. Schapire and Y. Singer, \u201cImproved Boosting Algorithms Using\r\nConfidence-rated Predictions.\u201d Machine Learning, vol. 37, no. 3, 1999,\r\npp. 297-336.\r\n[21] J. Friedman, T. Hastie, and R. Tibshirani, \u201cAdditive Logistic Regression:\r\na Statistical View of Boosting,\u201d The Annals of Statistics, vol.28, no.2,\r\n2000, pp. 337-407.\r\n[22] L. L. Huang, A. Shimizu, \u201cA multi-expert approach for robust face\r\ndetection,\u201d Pattern Recognition, vol. 39, 2006, pp. 1695-1703.\r\n[23] T. Ojala, M. Pietikainen, and T. Maenpaa, \u201cMultiresolution gray-scale\r\nand rotation invariant texture classification with local binary patterns,\u201d\r\nIEEE Trans. on PAMI, vol. 24, no. 7, 2002, pp. 971\u2013987.\r\n[24] V. Vezhnevets, V. Sazonov and A. Andreeva, \u201cA Survey on Pixel-Based\r\nSkin Color Detection Techniques\u201d Proc. of Graphicon conference, 2003.\r\n[25] G. Pajares and J. M. de la Cruz\u201d A wavelet-based image fusion tutorial\u201d,\r\nPattern Recognition Volume 37, Issue 9, September (2004), pp. 1855-\r\n1872 ","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 97, 2015"}