Blood Vessel Segmentation for IRIS in Unconstrained Environments using Moment Method

International Journal of Computer Science and Engineering
© 2018 by SSRG - IJCSE Journal
Volume 5 Issue 8
Year of Publication : 2018
Authors : Utkarsh Chouhan, H N Verma
: 10.14445/23488387/IJCSE-V5I8P103

pdf
Citation:
MLA Style:

Utkarsh Chouhan, H N Verma, "Blood Vessel Segmentation for IRIS in Unconstrained Environments using Moment Method" SSRG International Journal of Computer Science and Engineering 5.8 (2018): 8-14.

APA Style:

Utkarsh Chouhan, H N Verma,(2018). Blood Vessel Segmentation for IRIS in Unconstrained Environments using Moment Method. SSRG International Journal of Computer Science and Engineering 5(8), 8-14.

Abstract:

In recent years the use of smart technology is increasing day by day and also to provide security to such devices biometric identification and recognition plays an important role. In biometric identification the one most efficient and reliable technique is found to Iris Recognition (IR). Previous iris recognition system (IRS) is restricted to focused on images acquired in limited environments likewise in laboratory for research. But, with the adaption of technology the scenario is changed. In this research, proposed Iris recognition using blood vessel segmentation (bvs). In preprocessing process, the iris image is improved using Adaptive Median Filter (AMF). After the bvs process, the segmented iris image is recognized using moment features. For feature extraction process the technique used is Standard Deviation (SD), Kurtosis, Skewness, Smoothness, Variance and Root Mean Square (RMS). For training process, extracted features are classified using well known Support Vector Machine (SVM) classifier. The performance of proposed work is evaluated using High Resolution Fundus (HRF) Image Database. The performance of proposed features is better as compared to previous work. The proposed IR approach is more secure and robust against blood vessel segmentation and has the ability to identify retinal images from the iris photograph images. Also the proposed result is more efficient in terms of accuracy as well as time complexity.

References:

[1] Mehdi Ghayoumi, “A review of multimodal biometric systems: Fusion methods and their applications,” IEEE/ACIS 14th International Conference on Computer and Information Science (ICIS), pp. 131-136, 2015. 
[2] Hajari, K. and Bhoyar, K., “A review of issues and challenges in designing Iris Recognition Systems for noisy imaging environment” In International Conference on Pervasive Computing (ICPC), pp. 1-6, IEEE,2015. 
[3] Supriya Mahajan, Karan Mahajan “A Survey on IRIS Recognition System: Comparative Study” International Journal on Recent and Innovation Trends in Computing and Communication, Volume: 5 Issue: 4, April 2017. 
[4] A.K.Jain,A.Ross, and S.Pankanti, “Biometrics: A Tool for Information Security”, IEEE Transactions on Information Forensics and Security,Vol.1,No.2,2006,pp. 125-143. 
[5] A. Radman et al., Automated segmentation of iris images acquired in an unconstrained environmentusing HOG-SVMand GrowCut, Digit. Signal Process. (2017), http://dx.doi.org/10.1016/j.dsp.2017.02.003. 
[6] TossyThomas,AnuGeorge,Dr.K P Indira Devi, Effective Iris Recognition System. RAEREST 2016, pp 464 – 472. 
[7] Naglaa F.Soliman, Essam Mohamed, FikriMagdi, FathiE.Abd El-Samie, AbdElnaby M, Efficient Iris Localization and Recognition, Optik - International Journal for Light and Electron Opticshttp://dx.doi.org/10.1016/j.ijleo.2016.11.150. 
[8] Aparna G. Gale, Dr. Suresh S. Salankar, Evolution of Performance Analysis of Iris Recognition System By using Hybrid Methods of feature Extraction and Matching by Hybrid Classifierfor Iris Recognition System, (ICEEOT) – 2016,pp 3259-3263. 
[9] V.Dorairaj,A. Schmid, and G. Fahmy,"Performance Evaluation of Iris Based Recognition System Implementing PCA and ICA Encoding Techniques", in Proceedings of SPIE,2005,pp.51-58. 
[10] Kien Nguyen, Clinton Fookes, Sridharan: “Fusing shrinking and Expanding Active Contour Models For Iris Segmentation”, 10th International Conference on Information Science, Signal Processing and their Applications, 10-13 May 2010, Renaissance Hotel, Kuala Lumpur. 
[11] www.massey.ac.nz/~mjjohnso/notes/59731/.../Adaptive%20Median%20Filtering.doc. 
[12] Kaushik Roy, Prabir Bhattacharya, and Ching Y. Suen: “Unideal Iris Segmentation Using Region-Based Active Contour Model” Springer-Verlag Berlin Heidelberg 2010. 
[13] S.Karthick, V.Thirumurugan “The Survey on Iris Recognition System” International Journal of Engineering Trends and Technology (IJETT) – Volume 9 Number 2 - Mar 2014. 
[14] High Resolution Fundus (HRF) Image Database https:11 www5.cs.fau .de/research/data/fundus-images/83. 
[15] https://en.wikipedia.org/wiki/Variance. 
[16] Bland, J.M.; Altman, D.G. (1996). "Statistics notes: measurement error". BMJ. 312(7047):1654. doi:10.1136/bmj.312.7047.1654. PMC 2351401.PMID 8664723. 
[17] https://en.wikipedia.org/wiki/Skewness. 
[18] https://en.wikipedia.org/wiki/Kurtosis. 
[19] https://en.wikipedia.org/wiki/Root_mean_square. 
[20] https://en.wikipedia.org/wiki/Smoothness. 
[21] Adam Czajka, Kevin W. Bowyer, Michael Krumdick, and Rosaura G. VidalMata “Recognition of image-orientation-based iris spoofing” IEEE Transactions On Information Forensics And Security, pages: 1-13, 2016. 
[22] https://en.wikipedia.org/wiki/Bayes_classifier 
[23] Kanchan S. Bhagat, Dr. Pramod B. Pati and Dr. Jitendra P Chaudhari, “Global LBP Features for Iris Recognition using Blood Vessel Segmentation”, SMART -2016 IEEE, pp 79-83. 
[24] Zuiderveld, Karel. “Contrast Limited Adaptive Histograph Equalization.” Graphic Gems IV. San Diego: Academic Press Professional, 1994. 474–485. 
[25] T.W. Ridler, S. Calvard, Picture thresholding using an iterative selection method, IEEE Trans. System, Man and Cybernetics, SMC-8 (1978) 630-632.

Key Words:

Biometric recognition; Iris Recognition; Iris segmentation; Accuracy; Adaptive Median Filter; Blood Vessel.