Development of biometric systems for passenger identification based on noise-resistant coding means

The paper deals with the issues of using the biometric technologies to establish identity of a passenger. The purpose of the article is to analyze the techniques of enhancing reliability of various biometric identification facilities by means of using error correction codes. The basic elements and the principle of the classical biometric system functioning are presented. On the basis of the International Civil Aviation Organization (ICAO) recommendations, the procedure features of pattern recognition are presented. The versions to adopt the biometric passenger authentication procedures are under consideration. The conclusion is drawn that with the centralized biometric databases the issues of confidentiality and information security exist. The problems are characterized by the possibility of biometric images compromise, which can potentially lead to the loss of their confidentiality and the impossibility of their further usage for personal identification. The passenger authentication procedure involving the simultaneous use of biometric parameters and contact-free SMART cards seems more reliable. SMART cards are used for distributed storage of biometric and other additional data, thus neutralizing the disadvantages of access to the centralized databases. It is shown that the subsequent step in the development of this domain is the application of biometric cryptography proposing "linking" encryption keys and passwords with the biometric parameters of the subject. Consideration is given to the principle of "fuzzy extractor" operation as one of the variants for the "biometrics-code" converter. Feasibility and necessity of upgrading the means of noise-resistant coding in the systems being studied are shown. The use of permutation decoding data algorithms capable of adequately corresponding to the particular problems of biometric identification is proposed. On the basis of the results of optical communication channels statistical modeling, the necessary and sufficient conditions for application of the permutation decoding tools for binary codes are determined. The problem to minimize memory amount for the permutation decoder cognitive map due to the permutation orbits allocation and usage of the generated loops combinations as pointers of reference plane is solved. The resulting algorithm for finding a unique orbit number and its corresponding reference plane by means of receiver formation of arbitrary parameters permutation from the set of permissible permutations is proposed.

1. Bolle, R.M., Connell, J.H., Pankanti, Sh., Ratha, N.K. and Senior, A.W. (2004). Guide to Biometrics. Springer-Verlag, New York, 364 p. DOI: 10.1007/978-1-4757-4036-3

2. Sinha, P., Balas, B., Ostrovsky, Y. and Russell, R. (2006). Face recognition by humans: nineteen results all computer vision researchers should know about. Proceedings of the IEEE, vol. 94, no. 11, pp. 1948–1962. DOI: 10.1109/JPROC.2006.884093

3. Jain, A.K., Duin, P.W. and Mao, J. (2000). Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 1, pp. 4–37. DOI: 10.1109/34.824819

4. Kryukov, D.A. (2012). Action models of personal identification systems with antinoise coding procedures. Scientific edition of Bauman MSTU Science & Education, no. 10. DOI: 10.7463/1012.0486630 (accessed 23.01.2021).

5. Juels, A. and Wattenberg, M. (1999). A fuzzy commitment scheme. Proceedings of the 6th ACM conference on Computer and communications security, pp. 28–36. DOI: 10.1145/319709.319714

6. Dodis, Y., Reyzin, L. and Smith, A. (2004). Fuzzy extractors: how to generate strong keys from biometrics and other noisy data. Advances in Cryptology – EUROCRYPT 2004: Lecture Notes in Computer Science. In Cachin C., Camenisch J.L. (eds.)., vol. 3027, pp. 523–540. DOI: 10.1007/978-3-540-24676-3_31 (accessed 28.01.2021).

7. Hao, F., Anderson, R. and Daugman, J. (2006). Combining crypto with biometrics effectively. IEEE Transactions on Computers, vol. 9, no. 55, pp. 1081–1088. DOI: 10.1109/TC.2006.138

8. Al-Saggaf, A.A. (2018). Secure method for combining cryptography with iris biometrics. Journal of Universal Computer Science, vol. 24, no. 4, pp. 341–356.

9. Peng, L., Xin, Y., Hua, Q., Kai, C., Eryun, L. and Jie, T. (2012). An effective biometric cryptosystem combining fingerprints with error correction codes. Expert Systems with Applications, vol. 39, pp. 6562–6574. DOI: 10.1016/j.eswa.2011.12.048 (accessed 23.01.2021).

10. Akhmetov, B.B., Ivanov, A.I., Funtikov, V.A., Bezyaev, A.V. and Malygina, E.A. (2014). Tekhnologiya ispolzovaniya bolshikh neyronnykh setey dlya preobrazovaniya nechetkikh biometricheskikh dannykh v kod klyucha dostupa: Monografiya [Technology of using large neural networks for converting fuzzy biometric data into access key code: Monograph]. Almaty: TOO "Izdatelstvo LEM", 144 p. (in Russian)

11. Gladkikh, A.A., Volkov, An.K., Volkov, Al.K. and Ibragimov, R.Z. (2019). Noiseless coding algorithm based on cognitive processing of biometric data in system of digital identification of passengers. Journal of Physics: Conference Series (ITBI 2019), vol. 1333, issue 3, pp. 1–5. DOI: 10.1088/1742-6596/1333/3/032022

12. Gladkikh, A.A., Volkov, Al.K., Volkov, An.K., Il'in, V.M. and Kozlov, D.A. (2019). Cognitive decoding of redundant block codes in the system of processing and protection of biometric data of air passengers. IOP Conference Series: Materials Science and Engineering (MIST: Aerospace2019), vol. 734, pp. 1–6. DOI: 10.1088/1757-899X/734/1/012163