The model is a reprint of an object in the image
https://doi.org/10.32362/2500-316X-2020-8-3-7-13
Abstract
The problem of facial image recognition (identification) is presented. The difference between facial image recognition and identification is shown. To solve the identification problem, a model of object reprint in the image was developed. This model solves the problem by representing the object in 3-dimensional form, which makes it possible to evaluate and form the necessary characteristics of the object in full, whereas in 2-dimensional form, it is impossible to do this. The model of an object reprint in an image can be used to create a reprint of any spatial objects. To train a reprint model of an object in an image, a multi-layer neural network is used, which is trained sequentially. A local detector for the facial image identification model has been developed to account for acceptable changes in angle, various noise, and different light levels. The binary value that is the result of model processing, represented as activation, determines the relation of a particular image to the corresponding class. The local detector is not only the main element of the model of the object reprint in the image, but it is also a separate mathematical construction. It accepts input data as two-dimensional images. The developed model of object reprint on the image completely solves the problem of identifying a person from the facial image as a whole in conditions of interference and regardless of changes in the angle.
About the Author
A. A. Kulikov
MIREA - Russian Technological University
Russian Federation
Russian Federation
Alexander А. Kulikov - Cand. Sci. (Engineering), senior lecturer, Department of Instrumental and Applied Software, Institute of Information Technologies, MIREA - Russian Technological University.
78, Vernadskogo pr., Moscow 119454.
References
1. Korotkov A.E., Trifonova E.E. Algorithm for calculation of the Levenshtein distance with a threshold value. Estestvennye i tekhnicheskie nauki = Natur. Tech. Sci. 2012;1:317-322 (in Russ.).
2. Kulikov A.A., Demkin D.V., Melkov A.E. The Analysis of the Maximum Face Compression Impact on Face Recognition Result. Perspektivy nauki = SCIENCE PROSPECTS. 2014;3(54):104-108 (in Russ.).
3. Kamyshinskii V.I., Smirnov D.A. Neironnye seti i ikh primenenie v sistemakh upravleniya i svyazi (Neural networks and their application in control and communication systems). Moscow: Goryachaya liniya - Telekom; 2002. 94 p. (in Russ.). ISBN 5-93517-094-9
4. Khaikin S. Neironnye seti: polnyi kurs (Neural networks: full course). Moscow: Vil'yams; 2008. 1104 p. (in Russ.). ISBN 978-5-8459-0890-2 [Haykin S. Neural Networks: A Comprehensive Foundation. NJ: Prentice Hall; 1998. 798 p.]
5. Brilyuk D.V., Starovoitov V.V. Raspoznavanie cheloveka po izobrazheniyu litsa i neirosetevye metody: obzornyi preprint (Facial recognition and neural network methods: a review preprint). Minsk: Institute of Tech. cybernetics of NAS of Belarus; 2001. 54 p. (in Russ.).
6. Zaichenko Yu.P. Nechetkie modeli i metody v intellektual'nykh sistemakh: uchebn. posobie dlya VUZov (Fuzzy models and methods in intelligent systems). Kiev: Slovo Publishing House; 2008. 344 p. (in Russ.).
7. Starovoitov V.V. Lokal’nye geometricheskie metody tsifrovoi obrabotki i analiza izobrazhenii (Local geometric methods of digital image processing and analysis). Minsk: Institute of Tech. cybernetics of NAS of Belarus; 1997. 284 p. (in Russ.).
8. Kulikov A.A. NEFCclass M neural network algorithm and implementation of the algorithm in Matlab. Informatsionnye tekhnologii modelirovaniya i upravleniya = Information technologies modeling and management. 2013;3(81):262-268 (in Russ.).
9. Kulikov A.A. A system for automatic identification of a person's face image from a video image. In: Proc. Career and education-2013. Moscow: MGOU Publishing House; 2013. P. 99-100 (in Russ.).
10. Baldin A.V., Eliseev D.V. Adaptive data model based on the multidimensional Electron space.journal. Nauka i obrazovanie = Science & education [electronic journal]. 2010. № 10 (in Russ.). http://technomag.edu.ru/doc/161410.html
11. Eliseev D.V. Baldin A.V. Algebra of multidimensional matrices for processing an adapted data model. Nauka i obrazovanie = Science & education [electronic journal]. 2011. № 7 (in Russ.). http://technomag.edu.ru/doc/199561.html
12. Korotkov A. Database index for approximate string matching. In: Proc. 4th Spring/Summer Young Researchers' Colloquium on Software Engineering. SYRCoSE '10. 2010. P. 136-140. https://doi.org/10.15514/syrcose-2010-4-27
13. Etemad K., Chellapa R. Discriminant Analysis for Recognition of Human Face Images. J. Opt. Soc. Am. А. 1997;14(8):1724-1733. https://doi.org/10.1364/JOSAA.14.001724
Supplementary files
|
|
1. To solve the identification problem, a model of the object reprint on the image was developed. This model solves the problem by representing the object in the 3-dimensional form, which allows you to evaluate and form the necessary characteristics of the object in full, whereas in the 2-dimensional form it is impossible to do this. The developed model of the object reprint on the image completely solves the problem of identifying a person from the facial image in conditions of interference and regardless of changes in the angle. | |
| Subject | ||
| Type | Исследовательские инструменты | |
View
(36KB)
|
Indexing metadata ▾ | |
To solve the identification problem, a model of the object reprint on the image was developed. This model solves the problem by representing the object in the 3-dimensional form, which allows you to evaluate and form the necessary characteristics of the object in full, whereas in the 2-dimensional form it is impossible to do this.
The developed model of the object reprint on the image completely solves the problem of identifying a person from the facial image in conditions of interference and regardless of changes in the angle.Review
For citations:
Kulikov A.A. The model is a reprint of an object in the image. Russian Technological Journal. 2020;8(3):7-13. (In Russ.) https://doi.org/10.32362/2500-316X-2020-8-3-7-13
Views:
721
Email this article 