Model of Automatic Classification and Localization of Images
The work is devoted to the identification of images in pictures, which is performed as a result of the classification and localization procedures. Analysis of models, methods and algorithms has shown that for solving the set task it is preferable to use machine learning, an artificial neural network...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Ministry of Education of the Republic of Belarus, Establishment The Main Information and Analytical Center
2019-05-01
|
| Series: | Цифровая трансформация |
| Subjects: | |
| Online Access: | https://dt.bsuir.by/jour/article/view/112 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557153195393024 |
|---|---|
| author | L. V. Serebryanaya K. Y. Bochkarev A. Y. Popitich |
| author_facet | L. V. Serebryanaya K. Y. Bochkarev A. Y. Popitich |
| author_sort | L. V. Serebryanaya |
| collection | DOAJ |
| description | The work is devoted to the identification of images in pictures, which is performed as a result of the classification and localization procedures. Analysis of models, methods and algorithms has shown that for solving the set task it is preferable to use machine learning, an artificial neural network and a genetic algorithm. The architecture of a convolutional artificial neural network is proposed. It can solve both the problem of classification and the problem of localizing images. First the network is trained, then a class is determined for the image fed to its input. Objects are localized in the image at the final stage of operations of the convolutional neural network. For this, the output values of the penultimate layer of the model are analyzed, after which the layers are traversed in the reverse order. Its goal is to find the regions with the highest response on the source image. The combined model showed acceptable results both in classification and in localization of objects. All parameters for the network are determined automatically using a genetic algorithm. Further improvement of the proposed model results will be performed by implementing distributed computing on it. |
| format | Article |
| id | doaj-art-1f28eadc4cbd4617aae852dcd21954f7 |
| institution | Kabale University |
| issn | 2522-9613 2524-2822 |
| language | Russian |
| publishDate | 2019-05-01 |
| publisher | Ministry of Education of the Republic of Belarus, Establishment The Main Information and Analytical Center |
| record_format | Article |
| series | Цифровая трансформация |
| spelling | doaj-art-1f28eadc4cbd4617aae852dcd21954f72025-02-03T05:39:02ZrusMinistry of Education of the Republic of Belarus, Establishment The Main Information and Analytical CenterЦифровая трансформация2522-96132524-28222019-05-0101434810.38086/2522-9613-2019-1-43-4882Model of Automatic Classification and Localization of ImagesL. V. Serebryanaya0K. Y. Bochkarev1A. Y. Popitich2Belarusian State University of Informatics and RadioelectronicsBelarusian State University of Informatics and RadioelectronicsBelarusian State University of Informatics and RadioelectronicsThe work is devoted to the identification of images in pictures, which is performed as a result of the classification and localization procedures. Analysis of models, methods and algorithms has shown that for solving the set task it is preferable to use machine learning, an artificial neural network and a genetic algorithm. The architecture of a convolutional artificial neural network is proposed. It can solve both the problem of classification and the problem of localizing images. First the network is trained, then a class is determined for the image fed to its input. Objects are localized in the image at the final stage of operations of the convolutional neural network. For this, the output values of the penultimate layer of the model are analyzed, after which the layers are traversed in the reverse order. Its goal is to find the regions with the highest response on the source image. The combined model showed acceptable results both in classification and in localization of objects. All parameters for the network are determined automatically using a genetic algorithm. Further improvement of the proposed model results will be performed by implementing distributed computing on it.https://dt.bsuir.by/jour/article/view/112identificationclassificationlocalizationmodel of artificial neural networkgenetic algorithm |
| spellingShingle | L. V. Serebryanaya K. Y. Bochkarev A. Y. Popitich Model of Automatic Classification and Localization of Images Цифровая трансформация identification classification localization model of artificial neural network genetic algorithm |
| title | Model of Automatic Classification and Localization of Images |
| title_full | Model of Automatic Classification and Localization of Images |
| title_fullStr | Model of Automatic Classification and Localization of Images |
| title_full_unstemmed | Model of Automatic Classification and Localization of Images |
| title_short | Model of Automatic Classification and Localization of Images |
| title_sort | model of automatic classification and localization of images |
| topic | identification classification localization model of artificial neural network genetic algorithm |
| url | https://dt.bsuir.by/jour/article/view/112 |
| work_keys_str_mv | AT lvserebryanaya modelofautomaticclassificationandlocalizationofimages AT kybochkarev modelofautomaticclassificationandlocalizationofimages AT aypopitich modelofautomaticclassificationandlocalizationofimages |