Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks
The article discusses the solution to the problem of choosing the architecture of a convolutional neural network for use in the computer vision of a smart vending refrigerator. Comparative tests decided the architectures of convolutional neural networks YOLOv2, YOLOv3, YOLOv4, Mask R-CNN, and YOLACT...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2023-01-01
|
Series: | E3S Web of Conferences |
Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/27/e3sconf_agritechviii2023_03010.pdf |
_version_ | 1797807888148725760 |
---|---|
author | Alekhina Anna E. Dorrer Mikhail G. Ovchinnikov Alexander G. |
author_facet | Alekhina Anna E. Dorrer Mikhail G. Ovchinnikov Alexander G. |
author_sort | Alekhina Anna E. |
collection | DOAJ |
description | The article discusses the solution to the problem of choosing the architecture of a convolutional neural network for use in the computer vision of a smart vending refrigerator. Comparative tests decided the architectures of convolutional neural networks YOLOv2, YOLOv3, YOLOv4, Mask R-CNN, and YOLACT ++ on a standard MS COCO dataset, and then on datasets formed from images of typical smart refrigerator products. As a result of comparative tests, the best performance was demonstrated by the YOLOv3 architecture, trained based on a normalized dataset, supplemented with examples with complex intersections of samples without preprocessing examples. The obtained results substantiated the architecture used in computer vision of serially produced "smart" vending machines. |
first_indexed | 2024-03-13T06:29:21Z |
format | Article |
id | doaj.art-ea5f695442ec499f9f92bd887fdce6e2 |
institution | Directory Open Access Journal |
issn | 2267-1242 |
language | English |
last_indexed | 2024-03-13T06:29:21Z |
publishDate | 2023-01-01 |
publisher | EDP Sciences |
record_format | Article |
series | E3S Web of Conferences |
spelling | doaj.art-ea5f695442ec499f9f92bd887fdce6e22023-06-09T09:11:05ZengEDP SciencesE3S Web of Conferences2267-12422023-01-013900301010.1051/e3sconf/202339003010e3sconf_agritechviii2023_03010Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networksAlekhina Anna E.0Dorrer Mikhail G.1Ovchinnikov Alexander G.2Reshetnev Siberian State University of Science and TechnologyReshetnev Siberian State University of Science and TechnologySolution FactoryThe article discusses the solution to the problem of choosing the architecture of a convolutional neural network for use in the computer vision of a smart vending refrigerator. Comparative tests decided the architectures of convolutional neural networks YOLOv2, YOLOv3, YOLOv4, Mask R-CNN, and YOLACT ++ on a standard MS COCO dataset, and then on datasets formed from images of typical smart refrigerator products. As a result of comparative tests, the best performance was demonstrated by the YOLOv3 architecture, trained based on a normalized dataset, supplemented with examples with complex intersections of samples without preprocessing examples. The obtained results substantiated the architecture used in computer vision of serially produced "smart" vending machines.https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/27/e3sconf_agritechviii2023_03010.pdf |
spellingShingle | Alekhina Anna E. Dorrer Mikhail G. Ovchinnikov Alexander G. Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks E3S Web of Conferences |
title | Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks |
title_full | Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks |
title_fullStr | Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks |
title_full_unstemmed | Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks |
title_short | Smart eco-friendly refrigerator based on implementation of architectures of convolutional neural networks |
title_sort | smart eco friendly refrigerator based on implementation of architectures of convolutional neural networks |
url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2023/27/e3sconf_agritechviii2023_03010.pdf |
work_keys_str_mv | AT alekhinaannae smartecofriendlyrefrigeratorbasedonimplementationofarchitecturesofconvolutionalneuralnetworks AT dorrermikhailg smartecofriendlyrefrigeratorbasedonimplementationofarchitecturesofconvolutionalneuralnetworks AT ovchinnikovalexanderg smartecofriendlyrefrigeratorbasedonimplementationofarchitecturesofconvolutionalneuralnetworks |