International Journal Of Advancement In Engineering Technology, Management and Applied Science (IJAETMAS) ISSN: 2349-3224 || www.ijaetmas.com || Volume 03 - Issue 11 || November - 2016 || PP. 120-124
Authentication System for IRIS Biometric Recognition Using Texture Analysis: A Review 1
Miss. Leena D. Bhaiya,2 Prof. AB. Gadicha
1
M.E. (Scholar), Department of Computer Science & Engg. P. R. Patil College of Engineering &Technology, Amravati,
2
Asst. Prof. Department of Computer Science & Engineering, P. R. Pote (Patil) Education and Welfare Trust’s College of Engineering & Management, Amravati
ABSTRACT A biometric system provides automatic identification of an individual based on a unique feature possessed by the individual. Iris recognition has emerged as one of the most preferred biometric modalities for automated personal identification. Iris is an internally protected organ whose texture is stable from birth to death, as its texture is unique in each individual, so it is reliable and accurate method of biometric technology. Recently, a human-in-the-loop iris recognition system wasdeveloped based on crypt detection and crypt matching.Iris recognition is listed as a high confidence biometric identification system as the recognized delicate texture stays the same for several decades. It’s not possible for two irises to produce the same code. This paper provides a review of majoriris recognition researches and various Iris Recognitiontechniques used by different researchers for eachrecognition step. Keywords: Biometric, Iris recognition, human-in-the-loop 1. INTRODUCTION Biometrics is a combination of “Bio” means life and “metrics” means measure. Biometrics is defined as the science and technology of measuring and analyzing biological aspects of human being. Biometric authentication is highly reliable as physical human characteristics are
more difficult to forge than security codes, passwords, and other security system.
Biometric systems work by first capturing a sample of the feature, such as recording a digital sound signal for voice recognition, or taking a digital color image for face recognition, thenthis sample is transformed using some mathematical function into a biometric template. The biometric template provides a normalized, efficient and highly discriminating representation of the feature, which can then be objectively compared with other templates in order to determine identity.A biometric which uses a feature that is highly unique is a good biometric. This decreases the chances of any two people having the same characteristics. www.ijaetmas.com
Page 120
International Journal Of Advancement In Engineering Technology, Management and Applied Science (IJAETMAS) ISSN: 2349-3224 || www.ijaetmas.com || Volume 03 - Issue 11 || November - 2016 || PP. 120-124
Based on fingerprints, facial features, voice, hand geometry, handwriting and iris biometric systems have been developed. Among all of the biometric identification systems Iris is taking too much attention because of its reliability and secure identification measures. Other significant qualities of the iris are uniqueness, universality, longevity, collectability, and anti tampering, which all ensure accurate identification of the individual[1]. Existence of the iris characteristics in each person refers to the Universality, whereas uniqueness refers to the ability to distinctly identify individual from his or her iris characteristics. The subtle textures shaping the iris have completely distinctive patterns that differentiate each person from another, far more than most of the other biometrics [1]. This means that no two people in the world would have the same iris eye print, even the left and right eyes of an individual and those between twins are different [2]. To make artificial copy of the iris isimpossible because of its distinctproperties. As the iris is closely connected to the human brain, it is the first part of the body to degenerate after death, and therefore, it is next to impossible to use an artificial iris or to use a dead person’s iris to fraudulently bypass a security system [3]. The Human Iris The iris is a thin circular anatomical structure in the eye. The function of iris is to control the diameter and size of the pupils and hence it controls the amount of light that progresses to the retina. Figure 1 shows front view of the iris. To control the amount of light entering the eye, the muscles associated with the iris either expand or contract the center aperture of the iris known as the pupil [4].
Figure 1: Front view of human eye 1.1 Motivation The motivation for this system is from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric measurement. In particular, it is known in the biomedical community that the irises are www.ijaetmas.com
Page 121
International Journal Of Advancement In Engineering Technology, Management and Applied Science (IJAETMAS) ISSN: 2349-3224 || www.ijaetmas.com || Volume 03 - Issue 11 || November - 2016 || PP. 120-124
distinct. Iris is an overt body, its appearance is amenable to remoteexamination with the aid of a machine-vision system 1.2 Objectives To study structures of iris recognition system. To identify the techniques of iris recognition system. To analyze and evaluate the performance of existing system. To develop algorithm to make the iris recognition accurate. To analyze the system performance with respect to the parameters FAR,FRR 1.3 Organization Section IIof this paper provides literature survey by various authors and existing system. Section III contains conclusion
2. LITERATURE SURVEY 2.1 Background History Daugman et al [2004] Integro-differential operator uses first order derivatives of image intensity to locate circular edges of iris and upper and lower eyelids. By varying the radius r and center (x,y) position of circular contour the operator searches for circular path for maximum change in pixel values. To achieve precise localization, the operator is applied iteratively with progressively reduced smoothing. In Daugman’s system, by quantizing local phase angle of imaginary and real parts of filtered image, feature vector of 2048b were generated.[5] Safaa S. Omran et al [2015] proposes Ridge Energy Detection (RED) algorithm which is used to create the iris template which is considered as one of the most accurate identification method to detect the iris features, also Hamming Distance (HD) is used to match between iris templates. The second enhancement is by choosing small size of the iris region that contain sufficient feature to distinguish between people. The two enhancement help to improve the time execution and the performance of the system.[6] Yang Hu, KonstantinosSirlantzis et al [2016] proposes the iris code calculation from the perspective of optimization and demonstrate that the traditional iris code is the solution of an optimization problem which minimizes the distance between the feature values and iris
www.ijaetmas.com
Page 122
International Journal Of Advancement In Engineering Technology, Management and Applied Science (IJAETMAS) ISSN: 2349-3224 || www.ijaetmas.com || Volume 03 - Issue 11 || November - 2016 || PP. 120-124
codes. Furthermore, it shows that more effective iris codes can be obtained by adding terms to the objective function of this optimization problem.[7] Gupta et al[2011] evaluated the existing performance ofiris recognition systems by using Matlab Image ProcessingToolbox. The proposed technique consist of several basicsteps including image acquisition, segmentation, normalization, image enhancementand image matching. The main advantage of theproposed technique is that accuracy andperformance can be achieved even if images are taken froma distance.[8] 2.2 Existing System In the existing system,new approach for detecting and matching iris crypts automatically is used. In detection method, it is able to capture iris crypts of various sizes. Matching scheme is designed to handle potential topological changes in the detection of the same crypt in different images. This approach outperforms the known visible-feature based iris recognition method on three different datasets.[9]
CONCLUSION The most unique and data rich physical structure on the human body is iris. It provides enough accuracy and safe recognition.The main drawback of existing system is that the image has some noise or distortion due to which the accuracy of the system is affected. Also the approach is carried out on only three datasets, if any other dataset is used then its accuracy will not remain the same.
REFERENCE [1]
K. Saminathan, et al. “Iris recognition based on kernels of support vector machine,” ICTACT J. Soft Comput., vol. 5, no. 5, pp. 889–895, 2015. S. Venkatraman and I. Delpachitra, “Biometrics in banking security: A case study,” Inform. Manage. Comput. Sec., vol. 16, no. 4, pp. 415–430, 2008.
[3]
S. M. S. Ahmad, B. M. Ali, and W. A. W. Adnan, “Technical issues and challenges of biometric applications as access control tools of information security,” Int. J. Innovative Comp. Inform. Control, vol. 8, no. 11,pp. 7983–7999, 2012.
[4]
PallaviKharat, ManjushaDeshmukh,” IRIS Recognition: A Review”, International Journal of Advanced Trends in Computer Science and Engineering, Vol.2 , No.1, pp
www.ijaetmas.com
Page 123
International Journal Of Advancement In Engineering Technology, Management and Applied Science (IJAETMAS) ISSN: 2349-3224 || www.ijaetmas.com || Volume 03 - Issue 11 || November - 2016 || PP. 120-124
93-97,2013. [5]
J. Daugman “How iris recognition works”, IEEE Trans. CSVT, vol. 14, no. 1, pp. 21 – 30. 2004.
[6]
Safaa S. Omran, Aqeel A. Al-Hillali,” Quarter of Iris Region Recognition Using the RED Algorithm”, 17th UKSIM-AMSS International Conference on Modelling and Simulation, pp 66-72,2015
[7]
Yang Hu, KonstantinosSirlantzis, and Gareth Howells,” IEEE -Transactions on Information Forensics and Security”,2016
[8]
Gupta, R. and H. Saini, 2011. Generation of Iris Template forrecognition of Iris in efficient Manner, International Journalof Computer Science and Technologies (IJCSIT), 2(4).
[9]
Jianxu Chen, FengShen, Danny Z. Chen and Patrick J. Flynn,” Iris Recognition Based on Human-Interpretable Features”, IEEE Transactions on Information Forensics and Security,2015
www.ijaetmas.com
Page 124
