An effective iris segmentation scheme for noisy images

• Autorzy: Jan Farmanullah , Min-Allah Nasro

Identyfikatory

DOI

10.1016/j.bbe.2020.06.002

• Języki publikacji: EN

Abstrakty

EN

Iris segmentation plays a critical role in the iris biometric systems. It has two modules: iris localization and noise detection. The first module demarcates the actual iris' inner and outer boundaries in input eyeimages. The second module detects and removes noise in the valid iris part. Researchers devised numerous iris segmentation and/or localization schemes, which are based on the histogram and thresholding, circular Hough transform (CHT), Integro-differential operator (IDO), active contour models, graph-cuts, or deep learning. It is observed that most contemporary schemes perform poorly when confronted with images containing noisy factors such as the eyebrows, eyelashes, contact lenses, non-uniform illumination, light reflections, defocus and/or eyeglasses. The performance of CHT and IDO against noise is found robust, but these operators are computationally expensive. On the other hand, the histogram and thresholding-based schemes are considered fast, but these are less robust against noise. Besides, most contemporary schemes mark iris contours with a circle approximation and offer no noise removal strategy. To address these issues, this study offers an effective iris segmentation algorithm. First, it applies an optimized coarse-to-fine scheme based on an adaptive threshold to mark iris inner boundary. Next, it detects and marks eyelashes adaptively. After that, it marks iris outer boundary via an optimized coarse- to-fine scheme. Then, it regularizes the non-circular iris' contours using the Fourier series. Finally, eyelids and reflections are marked in the iris polar form. The proposed scheme shows better results on the CASIA-Iris-Interval V3.0, IITD V1.0, and MMU V1.0 iris databases.

Słowa kluczowe

EN

iris biometrics; pupil localization; iris localization; iris segmentation

PL

biometryka tęczówki; lokalizacja tęczówki; segmentacja tęczówki

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1064--1080
• Opis fizyczny: Bibliogr. 37 poz., rys., tab., wykr.

Twórcy

autor

Jan Farmanullah

• Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, Saudi Arabia

autor

Min-Allah Nasro

• Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, Saudi Arabia

Bibliografia

• [1] Gawande U, Zaveri M, Kapur A. Multi-algorithmic approaches to iris recognition. Biom Technol Today 2011;2011(4):8–10.
• [2] Wildes RP. Iris recognition: an emerging biometric technology. Proc IEEE 1997;85(9):1348–63.
• [3] Daugman JG. High confidence visual recognition of persons by a test of statistical independence. IEEE Trans Pattern Anal Mach Intell 1993;15(11):1148–61.
• [4] NSTC, NSTC website: http://www.biometrics.gov/ReferenceRoom/Introduction. aspx [accessed 20.09.19].
• [5] Khakzar M, Pourghassem H. A retinal image authentication framework based on a graph-based representation algorithm in a two-stage matching structure. Biocybern Biomed Eng 2017;37(4):742–59.
• [6] Kadi KL, Selouani SA, Boudraa B, Boudraa M. Fully automated speaker identification and intelligibility assessment in dysarthria disease using auditory knowledge. Biocybern Biomed Eng 2016;36(1):233–47.
• [7] Nguyen K, Fookes C, Jillela R, Sridharan S, Ross A. Long range iris recognition: a survey. Pattern Recognit 2017;72:123–43.
• [8] Donida Labati R, Muñoz E, Piuri A, Scotti F. Non-ideal iris segmentation using Polar Spline RANSAC and illumination compensation. Comput Vis Image Understand 2019;188:102787.
• [9] Wang C, Muhammad J, Wang Y, He Z, Sun Z. Towards complete and accurate iris segmentation using deep multi- task attention network for non-cooperative iris recognition. IEEE Trans Inf Forensics Secur 2020;15:2944–59.
• [10] Vyas R, Kanumuri T, Sheoran G, Dubey P. Recent trends of ROI segmentation in iris biometrics: a survey. Int J Biom 2019;11:274–307.
• [11] Bowyer KW, Hollingsworth K, Flynn PJ. Image understanding for iris biometrics: a survey. Comput Vis Image Understand 2008;110(2):281–307.
• [12] Jan F. Segmentation and localization schemes for non-ideal iris biometric systems. Signal Process 2017;133:192–212.
• [13] Ma L, Li H, Yu K. Fast iris localization algorithm on noisy images based on conformal geometric algebra. Digit Signal Process 2020;100:102682.
• [14] MMU_Iris_Database, https://www.cs.princeton.edu/andyz/downloads/ MMUIrisDatabase.zip.
• [15] IITD_iris_databases, http://www.iitd.ac.in/ [accessed 02.08.19].
• [16] CASIA_Iris_Database, http://www.cbsr.ia.ac.cn/english/IrisDatabase.asp.
• [17] Sardar M, Mitra S, Shankar BU. Iris localization using rough entropy and CSA: a soft computing approach. Appl Soft Comput 2018;67:61–9.
• [18] Soliman NF, Mohamed E, Magdi F, El-Samie FEA, Muhmmad A. Efficient iris localization and recognition. Optik 2017;140:469–75.
• [19] Mehrotra H, Sa PK, Majhi B. Fast segmentation and adaptive SURF descriptor for iris recognition. Math Comput Model 2013;58:132–46.
• [20] Boonchuan T, Setumin S, Radman A, Suandi SA. Efficient iris and eyelids detection from facial sketch images. Electron Lett Comput Vis Image Anal 2018;17(1):16–28.
• [21] Ahad MAR, Paul T, Shammi U, Kobashi S. A study on face detection using viola-jones algorithm for various backgrounds. Angels and distances. Appl Soft Comput 2018.
• [22] Jan F. Non-circular iris contours localization in the visible wavelength eye images. Comput Electr Eng 2017;62:166–77.
• [23] Abdullah MAM, Dlay SS, Woo WL, Chambers JA. Robust iris segmentation method based on a new active contour force with a noncircular normalization. IEEE Trans Syst Man Cybern: Syst 2017;47(12):3128–41.
• [24] Li YH, Huang PJ, Juan Y. An efficient and robust iris segmentation algorithm using deep learning. Mob Inf Syst 2019;2019:1–14.
• [25] Jan F, Usman I. Iris segmentation for visible wavelength and near infrared eye images. Optik 2014;125(16):4274–82.
• [26] Min T-H, Park R-H. Eyelid and eyelash detection method in the normalized iris image using the parabolic Hough model and Otsu's thresholding method. Pattern Recognit Lett 2009;30(12):1138–43.
• [27] Mire A, Dhote B. Iris recognition system with accurate eyelash segmentation & improved FAR, FRR using textural & topological features. Int J Comput Appl 2010;7.
• [28] Jan F. Development and analysis of robust iris segmentation algorithms for non ideal iris recognition system. PhD Thesis COMSATS Univeristy Islamabad; 2014.
• [29] Gonzalez RC, Woods RE. Digital image processing. 2nd ed. Prentice Hall Professional Technical Reference; 1992 (April 30).
• [30] Masek LKP. Matlab source code for a biometric identification system based on iris pattern. The School of Computer Science and Software Engineering. The University of Western; 2003.
• [31] Khan TM, Aurangzeb Khan M, Malik SA, Khan SA, Bashir T, Dar AH. Automatic localization of pupil using eccentricity and iris using gradient based method. Optics Lasers Eng 2011;49(2):177–87.
• [32] Ibrahim MT, Khan MT, Khan SA, Guan L. Iris localization using local histogram and other image statistics. Optics Lasers Eng 2012;50(5):645–54.
• [33] Jan F, Usman I, Agha S. Iris localization in frontal eye images for less constrained iris recognition systems. Digit Signal Process 2012;22:971–86.
• [34] Ross A, Shah S. Segmenting non-ideal irises using geodesic active contours. 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference; 2006.
• [35] Wan H-L, Li ZC, Qiao JP, Li BS. Non-ideal iris segmentation using anisotropic diffusion. IET Image Process 2013;7:111–20.
• [36] Masek, L., Recognition of Human Iris Patterns for Biometric Identification.
• [37] Basit A, Javed MY. Iris localization via intensity gradient and recognition through bit planes. Machine Vision, 2007. International Conference on ICMV 2007; 2007.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).