Methods of the development of the architecture of the neural networks for identification and authentication of individuals
This paper deals with the neural network methods of the implementation of systems of identification ofindividuals based on videos and photographs. Over the last few decades, it has been considered to be oneof the most powerful tools and has become very popular in the literature as it is able to hand...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Al-Farabi Kazakh National University
2020-12-01
|
| Series: | Physical Sciences and Technology |
| Subjects: | |
| Online Access: | https://phst.kaznu.kz/index.php/journal/article/view/217/219 |
| _version_ | 1818908691499319296 |
|---|---|
| author | O. Y. Golikov M. A. Ramos |
| author_facet | O. Y. Golikov M. A. Ramos |
| author_sort | O. Y. Golikov |
| collection | DOAJ |
| description | This paper deals with the neural network methods of the implementation of systems of identification ofindividuals based on videos and photographs. Over the last few decades, it has been considered to be oneof the most powerful tools and has become very popular in the literature as it is able to handle a hugeamount of data. The neural network architectures used in modern biometric identification systems havebeen reviewed. Based on the research conducted in this field, an approach was developed that can improvethe accuracy of object recognition in photo and video images by increasing the quality of the attributes ofthe weights and reducing the number of the weights, as well as the number of the connections. The basis ofthe developed neural network model is a multilayer perceptron; the main system is a convolutional neuralnetwork. The neural network model has been implemented using the Python programming language withthe most popular machine learning libraries Keras and TensorFlow. In addition, we will also enumerate theparameters that affect CNN efficiency. |
| first_indexed | 2024-12-19T22:15:02Z |
| format | Article |
| id | doaj.art-93454ca89ab94ef9ac34b5b70e0eed6e |
| institution | Directory Open Access Journal |
| issn | 2409-6121 2522-1361 |
| language | English |
| last_indexed | 2024-12-19T22:15:02Z |
| publishDate | 2020-12-01 |
| publisher | Al-Farabi Kazakh National University |
| record_format | Article |
| series | Physical Sciences and Technology |
| spelling | doaj.art-93454ca89ab94ef9ac34b5b70e0eed6e2022-12-21T20:03:47ZengAl-Farabi Kazakh National UniversityPhysical Sciences and Technology2409-61212522-13612020-12-0173-4444910.26577/phst.2020.v7.i2.07Methods of the development of the architecture of the neural networks for identification and authentication of individualsO. Y. Golikov0M. A. Ramos1Autonomous University of MadridAutonomous University of MadridThis paper deals with the neural network methods of the implementation of systems of identification ofindividuals based on videos and photographs. Over the last few decades, it has been considered to be oneof the most powerful tools and has become very popular in the literature as it is able to handle a hugeamount of data. The neural network architectures used in modern biometric identification systems havebeen reviewed. Based on the research conducted in this field, an approach was developed that can improvethe accuracy of object recognition in photo and video images by increasing the quality of the attributes ofthe weights and reducing the number of the weights, as well as the number of the connections. The basis ofthe developed neural network model is a multilayer perceptron; the main system is a convolutional neuralnetwork. The neural network model has been implemented using the Python programming language withthe most popular machine learning libraries Keras and TensorFlow. In addition, we will also enumerate theparameters that affect CNN efficiency.https://phst.kaznu.kz/index.php/journal/article/view/217/219biometric identification of individualsthree-dimensional object recognitionconvolutional neural networkdeep machine learning |
| spellingShingle | O. Y. Golikov M. A. Ramos Methods of the development of the architecture of the neural networks for identification and authentication of individuals Physical Sciences and Technology biometric identification of individuals three-dimensional object recognition convolutional neural network deep machine learning |
| title | Methods of the development of the architecture of the neural networks for identification and authentication of individuals |
| title_full | Methods of the development of the architecture of the neural networks for identification and authentication of individuals |
| title_fullStr | Methods of the development of the architecture of the neural networks for identification and authentication of individuals |
| title_full_unstemmed | Methods of the development of the architecture of the neural networks for identification and authentication of individuals |
| title_short | Methods of the development of the architecture of the neural networks for identification and authentication of individuals |
| title_sort | methods of the development of the architecture of the neural networks for identification and authentication of individuals |
| topic | biometric identification of individuals three-dimensional object recognition convolutional neural network deep machine learning |
| url | https://phst.kaznu.kz/index.php/journal/article/view/217/219 |
| work_keys_str_mv | AT oygolikov methodsofthedevelopmentofthearchitectureoftheneuralnetworksforidentificationandauthenticationofindividuals AT maramos methodsofthedevelopmentofthearchitectureoftheneuralnetworksforidentificationandauthenticationofindividuals |