Recording Identities Using Iris Scanners - Free Essay

Automatic recognition of individuals

John Daugman also emphasizes the wide acceptance of automatic recognition of individuals. Daugman developed algorithms for recognizing persons by their iris patterns. These algorithms have been tested in many laboratory and field trials, and the results show no false matches in numerous comparison tests. In his article “How Iris Recognition Works” (2004), Daugman argues that the key issue in many recognition problems is the relation between intra-class and inter-class variability. In this case, a researcher will only manage to reliably classify objects if the variance among different instances or cases of a given class is just under the variability between different classes (Daugman, 2004). In face recognition, for instance, problems arise from the reality that the face, as a social organ, can undergo changes that make it display a variety of expressions. Beside, the face is a typical case of a three dimensional object whose image normally vary with viewing angle, illumination, accoutrements, age, and pose. The author maintains that the imaging system ought to resolve a minimum of 70 pixels (iris radius) to effectively capture the rich details of the iris patterns.

Is your time best spent reading someone else’s essay? Get a 100% original essay FROM A CERTIFIED WRITER!

Order now

Stan Z. Li’s Encyclopedia of Biometrics (2009) analyzes modalities, concepts, devices, algorithms, performance testing, security, and standardization in biometrics. Li offers practical knowledge for industry practitioners and research scientists in a range of fields such as computer scientists and other professionals in the fields of biomedicine, management science, statistics, and engineering (Li, 2009). The author believes that biometrics security system is an important technology that can help in the identification and authentication of individuals. Li pointed out common examples of biometric systems applications such as fingerprint recognition, appearance models, and face recognition.

Kavitha, Gowtham, and Arul Karthick (2015) focus on iris recognition and its potential value in personal identification and verification. The trio draws attention to recent research results which suggest that several covariates such as sensor interoperability and pupil dilation affect iris features. The presence of transparent and color cosmetic contact lenses has also widely affected iris recognition (Kavitha, Gowtham, & Karthick, 2015). The authors suggest that the first step to improving the reliability and usability of iris recognition is through detection of the presence of a contact lens. They assert that a novel lens detection algorithm anchored in Modified LBF based classification is vital for detecting the textured lens from the iris image. However, the trio proposes Haar texture feature. In particular, the Haar wavelet is a simple wavelet that can transform huge data sets to fairly smaller representations.

Significance of Cyber-Physical Systems and Internet of Things to UAE’s security

IoT-enabled CPS is usually very large thus raising a number of challenges such as system-level management and control to data analytics. Some of the system-level challenges include well-defined control interfaces or borders for IoT technologies, various IoT standards, effective development of management platforms, and scalable methods/techniques for global system control (O'Brien, 2016). Data related challenges, on the other hand, include effective data collection, data latency, cleaning and storage, and real-time analytics. Internet of Things is driving more data into enterprise. IoT-enabled architecture, APIs, and protocols play an integral role in designing Cyber Physical Systems and implementing applications needed. In particular, APIs facilitate the process of collecting, processing, and managing large data sets. IoT-based CPS also support complex processes in an attempt to control and manage such systems at different scales.

Meanwhile, Big Data has clearly become a crucial component for extracting value from data. This domain is anticipated to get bigger and more advanced with the large deployments of IoT systems. These large deployments will in turn put more challenge, stress and burden on the data analytics researchers. UAE’s transport system is likely to achieve a milestone with incorporation of IoT-based CPS (O'Brien, 2016). Cloud Computing platforms and infrastructures can help to efficiently and effectively support the large-scale nature of IoT-based CPS. In particular, Cloud Computing platforms provide flexible resource virtualization, high-powered storage for data streams, computational power. These infrastructures and platforms will also ensure privacy, safety, and security of data. Successful integration of networked physical systems, devices, and people provides a tantalizing vision as far as future possibilities of IoT are concerned. IoT is likely to become a vibrant and dynamic component of the digital business landscape.

IoT often considers all-encompassing presence in the settings or environment that contains a variety of things. The things may interact with each other as well as cooperate with other things through wired and wireless connections, and distinctive addressing schemes to generate new services/applications and accomplish common goals. CPS represents the next generation of embedded intelligent ICT systems, ostensibly interconnected, collaborative, autonomous, and interdependent (Bordel-Sánchez et al., 2016). It provides communication and computing, and control of physical processes and components in a range of applications. On the other hand, Smart Objects normally act as intelligent agents that cooperate with other agents, as well as exchange vital information with other human users and computing devices within the interconnected CPS.

Conclusion

In summary, Smart Travel allows passengers to move through security and immigration after checking by interacting mainly with innovative technology. Iris recognition technology has gained unprecedented prominence due to the growing demand for security in the daily lives of individuals and organizations in the country. Biometric security devices often measure unique traits of an individual, such as the iris pattern, finger print patterns, or voice pattern. Biometric data play a crucial role in identity management in the UAE and around the world. It has particularly helped the country to reduce integrity risks and fraud. With biometrics, it becomes extremely hard for attackers to break into the UAE’s security system. However, it is easier for the attacker to have physical access to the storage device and fraudulently obtain the information contained inside. It is imperative that the vulnerabilities of biometric systems and other technologies to external attacks are studied in order to improve their performance, robustness, and reliability. An automatic recognition system would help to manage and control both direct and indirect attacks. Meanwhile, market studies and predictions continue to give high figures for IoT-enabled devices on the UAE’s transport systems and consumer arena at large.

References

Al Kuttab, J. (2016). Abu Dhabi Airport first in region to create “Smart Travel’. April 13, 2016, retrieved from

Al-Raisi, A. & Al-Khouri, A. (2008), “Iris recognition and the challenge of homeland and boarder control security in UAE,” Telematics and Informatics, 25 (2008) 117-132.

Bansal, A., Agarwal, R., & Sharma, R. K. (2016). Statistical feature extraction based iris recognition system. Sadhana, 41(5), 507-518.

Bordel-Sánchez, B., Alcarria, R., Sánchez de Rivera, D., & Sánchez-Picot, A. (2016). Predictive algorithms for mobility and device lifecycle management in Cyber-Physical Systems. EURASIP Journal on Wireless Communications & Networking, 2016(1), 1-13.

Daugman, J. (2004), “How Iris Recognition Works,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 14, No. 1, January 20014, p. 21-30.

Galbally, B., Fierrez, J. & Ortega-Garcia, J. (n.d.), “Vulnerabilities in Biometric Systems: Attacks and Recent Advances in Liveness Detection,” p. 1-8.

Galbally, J., Ross, A., Gomez-Barrero, M., Fierrez, J., Ortega-Garcia, J. (2012). From the Iriscode to the Iris: A New Vulnerability of Iris Recognition Systems,” July 6, 2012, p. 1-24.

Hofbauer, H., Alonso-Fernandez, F., Bigun, J., & Uhl, A. (2016). Experimental analysis regarding the influence of iris segmentation on the recognition rate. IET Biometrics, 5(3), 200-211.

Kavitha, V., Gowtham, M., & Karthick, V., J. (2015), “Effect of Textured Contact Lenses on Iris Recognition,” International Journal of Science Technology & Management, Vol. No. 04, Issue No. 01, February 2015, p. 372-380.

Li, S., Z. (2009). Encyclopedia of Biometrics. Springer.

O'Brien, H. M. (2016). The Internet of Things. Journal of Internet Law, 19(12), 1-20.