10.14489/vkit.2016.04.pp.023-029

DOI: 10.14489/vkit.2016.04.pp.023-029

Блохинов Ю. Б., Горбачев В. А.
АНАЛИЗ ПОДЛИННОСТИ ОБРАЗЦОВ ЗАЩИЩЕННОЙ ПЕЧАТНОЙ ПРОДУКЦИИ С ИСПОЛЬЗОВАНИЕМ СМАРТФОНА
(c. 23-29)

Аннотация. Разработан метод аутентификации защищенных печатных оттисков по цифровому снимку на основе серийных смартфонов. Метод не требует разработки дизайна и внедрения в изделие новых защитных элементов и основан на применении цифровых методов анализа и обработки изображений, позволяющих осуществлять автоматический поиск и верификацию известных защитных элементов оттиска. Особенность предлагаемого подхода связана с построением набора признаков для каждого типа образцов и последующей их классификацией с машинным обучением на основе обучающей выборки.

Ключевые слова: защищенный печатный оттиск; банкнота; мобильное устройство; смартфон; анализ изображений; подделки; идентификация; аутентификация; набор признаков; классификация.

Blokhinov Yu. B., Gorbachev V. A.
THE AUTHENTICITY ANALYSIS OF SAMPLES OF THE PROTECTED PRINTED MATERIALS WITH USE OF THE SMARTPHONE
(pp. 23-29)

Abstract. The article is devoted to one of actual tasks of creating high-tech software applications based on mobile devices. The task represents not only technical, but also scientific interest because limited computational power of smartphones impose additional requirements of the algorithms developed for such programs, especially in the almost real time conditions. During authentication the coordinates of interest zones on the image are defined, attribute vectors are calculated and classification of a sample is made. This method doesn't demand development and deployment of new protective graphic elements in a print and is based on application of digital methods of the analysis and digital image processing allowing to reveal and analyze fine details of patterns and on the basis of this analysis to classify sample as belonging to one of two classes: originals or imitations. Thus along with classical methods of Fourier, Laplace and operators of interest some effective modern approach as classification with machine training, in this case the support vector machine method (SVM) is used. In conclusion, the method developed is tested on the created base of samples of the protected printed materials. It is shown that the speed of data processing and reliability of result meet the requirements of the initial objective. In conclusion, the authors describe the program application realized on the mobile phone Samsung Galaxy S4 and give results of its testing on the created base of the protected printed materials. Control testing of program on the test base demonstrated rather high results both on time and on reliability of recognition of the samples under test. Finally, the method constructed includes a number of the interesting algorithmic decisions allowing the authors to perform the identification of protected printing prints in almost real time mode with high reliability of result.

Keywords: Protected Print; Banknote; Mobile Device; Smartphone; Image Analysis; Counterfeits; Identification; Authentication; Feature Vector; Classification.

+ - Информация об авторах (About the Authors) Click to collapse

Рус

Ю. Б. Блохинов, В. А. Горбачев (ФГУП «Государственный научно-исследовательский институт авиационных систем» ГНЦ РФ, Москва) E-mail: Этот e-mail адрес защищен от спам-ботов, для его просмотра у Вас должен быть включен Javascript

Eng

Yu. B. Blokhinov, V. A. Gorbachev (State Research Institute of Aviation Systems State Scientific Center of Russian Federation, Moscow) E-mail: Этот e-mail адрес защищен от спам-ботов, для его просмотра у Вас должен быть включен Javascript

+ - Библиографический список (References) Click to collapse

Рус

1. Banknote Authentication with Mobile Devices / V. Lohweg et al. // Proc. SPIE, Media Watermarking, Security, and Forensics. 2013. V. 8665. Burlingame, California, USA, March 22, 2013. doi:10.1117/ 12.2001444.
2. Pat. EP 2000992 А1. Classification International: G07D7/00, G07D7/20. Authentication of Security Documents, in Particular of Banknotes / Lohweg V., Gillich E., Schaede J; Аpplicant Kba-Giori S. A. № EP20070109470; аppl. 01.06.2007; рubl.10.12. 2008.
3. Lohweg V. Renaissance of Intaglio // Keesing Journal of Documents & Identity. 2010. № 33. Р. 35 – 41.
4. Lohweg V., Schaede J. Document Production and Verification by Optimization of Feature Platform Exploitation / Optical Document Security the Conference on Optical Security and Counterfeit Detection II. San Francisco, CA, USA, 20 – 22 January, 2010. San Francisco, 2010. Р. 1 – 15.
5. Mobile Devices for Banknote Authentication – is it Possible? / V. Lohweg et al. // The Conference on Optical Security and Counterfeit Detection III. San Francisco, CA, USA, 18 – 20 January, 2012. San Francisco, 2012. Р. 1 – 15.
6. Enhancing Privacy and Security in RFID-Enabled Banknotes / C-N. Yang et al. // IEEE International Symposium on Parallel and Distributed Processing with Applications, 2009. Р. 439 – 444.
7. Omatu S., Yoshioka M., Kosaka, Y. Bank Note Classification Using Neural Networks // IEEE Conf. on Emerging Technologies and Factory Automation, 2007. Р. 413 – 417. doi: 10.1109/EFTA.2007.4416797.
8. Идентификация образцов защищенной печатной продукции с использованием смартфона / Ю. Б. Блохинов и др. // Вестник компьютерных и информационных технологий. 2016. № 3. С. 11 – 17.
9. Гонсалес Р., Вудс Р. Цифровая обработка изображений: пер. с англ. M.: Техносфера, 2005. 1072 с.
10. Шапиро Л., Стокман Дж. Компьютерное зрение: пер. с англ. М.: БИНОМ, 2006. 752 с.
11. Department of Computer Science [Электронный ресурс] // Blob Detection: офиц. сайт. URL: http://www.cs. unc.edu/~lazebnik/spring11/lec08_blob.pdf (дата обращения: 22.12.2015).
12. Harris C., Stephens M. A Combined Corner and Edge Detector // Proc. of the 4th Alvey Vision Conference. September, Manchester, UK. 1988. Р. 147 – 151.
13. Cristianini N., Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, 2003. 168 р.
14. Wikipedia [Электронный ресурс]: офиц. сайт. URL: https://en.wikipedia.org/wiki/Support_vector_machine (дата обращения: 22.12.2015).
15. Molina L. C., Belanche L., Nebot A. Feature Selection Algorithms: A Survey And Experimental Evaluation // Proc. of the IEEE International Conference on Data Mining. Maebashi City, Japan, 9 – 12 December 2002. Р. 306 – 313.

Eng

1. Lohweg V. et al. (2013). Banknote authentication with mobile devices. Proc. SPIE 8665, Media Watermarking, Security, and Forensics. 22 March 2013. doi:10.1117/ 12.2001444.
2. Lohweg V., Gillich E., Schaede J; Аpplicant Kba-Giori S. A. (2008). Authentication of security documents, in particular of banknotes. Pat. EP 2000992.
3. Lohweg V. (2010). Renaissance of intaglio. Keesing Journal of Documents & Identity, 33, pp. 35-41.
4. Lohweg V., Schaede J. (2010). Document production and verification by optimization of feature platform exploitation. Optical Document Security the Conference on Optical Security and Counterfeit Detection II. 20 – 22 January 2010. San Francisco, CA, USA, pp. 1-15.
5. Lohweg V. et al. (2012). Mobile devices for banknote authentication – is it Possible? The Conference on Optical Security and Counterfeit Detection III. 18 – 20 January 2012. San Francisco, CA, USA, pp. 1-15.
6. Yang C-N. et al. (2009). Enhancing privacy and security in RFID-enabled banknotes. IEEE International Symposium on Parallel and Distributed Processing with Applications, pp. 439-444.
7. Omatu S., Yoshioka M., Kosaka Y. (2007). Bank note classification using neural networks. IEEE Conference on Emerging Technologies and Factory Automation, pp. 413-417, doi: 10.1109/EFTA.2007.4416797.
8. Blokhinov Yu. B., Gorbachev V. A., Rakutin Yu. O., Volkov V. V. (2016). Identification of samples of the protected printed materials with use of the smartphone. Vestnik komp'iuternykh i informatsionnykh tekhnologii, (3), pp. 11-17, doi: 10.14489/vkit.2016.03.pp.011-017
9. Gonsales R., Vuds R. (2005). Digital image processing. Moscow: Tekhnosfera.
10. Shapiro L., Stokman Dzh. (2006). Computer vision. Moscow: BINOM.
11. Department of computer science. Blob Detection: official site. Available at: http://www.cs. unc.edu/~lazebnik/ spring11/lec08_blob.pdf (Accessed: 22.12.2015).
12. Harris C., Stephens M. (1988). A combined corner and edge detector. Proc. of the 4th Alvey Vision Conference. September, UK, Manchester, pp. 147-151.
13. Cristianini N., Shawe-Taylor J. (2003). An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press.
14. Wikipedia: official site. Available at: https:// en.wikipedia.org/ wiki/Support_vector_machine (Accessed: 22.12.2015).
15. Molina L. C., Belanche L., Nebot A. (2002). Feature selection algorithms: a survey and experimental evaluation. Proc. of the IEEE International Conference on Data Mining. Maebashi City, Japan. 9-12 December 2002, pp. 306-313.

+ - Заказать электронную версию статьи (Purchase digital version of a single article) Click to collapse

Рус

Статью можно приобрести в электронном виде (PDF формат).

DOI: 10.14489/vkit.2016.04.pp.023-029

Скопируйте DOI статьи и перейдите по ссылке https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-vestnik-kompyuternyh-i-informatsionnyh-tehnologiy

В комментарии к заказу обязательно укажите DOI статьи.

Eng

This article is available in electronic format (PDF).

DOI: 10.14489/vkit.2016.04.pp.023-029

Copy the article DOI and follow the link https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-vestnik-kompyuternyh-i-informatsionnyh-tehnologiy

Please specify the article DOI in the order comments.