Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller
The paper is devoted to solving the problem of using neural networks for real-time image recognition on low-power portable devices running on microcontrollers. The ESP-32© CAM microcontroller was used as the target device, on which an artificial neural network was deployed, written using the Python...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Igor Sikorsky Kyiv Polytechnic Institute
2023-05-01
|
Series: | Mìkrosistemi, Elektronìka ta Akustika |
Subjects: | |
Online Access: | http://elc.kpi.ua/article/view/277487 |
_version_ | 1797744859414528000 |
---|---|
author | Rostyslav Dmytrovych Sharuiev Pavlo Vasylovych Popovych |
author_facet | Rostyslav Dmytrovych Sharuiev Pavlo Vasylovych Popovych |
author_sort | Rostyslav Dmytrovych Sharuiev |
collection | DOAJ |
description |
The paper is devoted to solving the problem of using neural networks for real-time image recognition on low-power portable devices running on microcontrollers. The ESP-32© CAM microcontroller was used as the target device, on which an artificial neural network was deployed, written using the Python® programming language and the Tensorflow© library for building neural networks. The performance of the microcontroller and personal computer for object detection using a neural network and their classification were compared in the paper. The image recognition time and percentage of correctly classified objects were compared. The paper shows that the number of training epochs affects the accuracy of object classification in the image. The obtained results show that increasing the number of training epochs increases the accuracy of object recognition using the studied neural network, but a significant increase in the number of epochs does not lead to a significant improvement in recognition accuracy. The difference in the obtained results for the microcontroller and personal computer image recognition accuracy ranges from 5%.
|
first_indexed | 2024-03-12T15:15:28Z |
format | Article |
id | doaj.art-e41385d65f2d47bab1253a3b510a6a0d |
institution | Directory Open Access Journal |
issn | 2523-4447 2523-4455 |
language | English |
last_indexed | 2024-03-12T15:15:28Z |
publishDate | 2023-05-01 |
publisher | Igor Sikorsky Kyiv Polytechnic Institute |
record_format | Article |
series | Mìkrosistemi, Elektronìka ta Akustika |
spelling | doaj.art-e41385d65f2d47bab1253a3b510a6a0d2023-08-11T13:57:25ZengIgor Sikorsky Kyiv Polytechnic InstituteMìkrosistemi, Elektronìka ta Akustika2523-44472523-44552023-05-0128210.20535/2523-4455.mea.277487Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM MicrocontrollerRostyslav Dmytrovych Sharuiev0Pavlo Vasylovych Popovych1National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” The paper is devoted to solving the problem of using neural networks for real-time image recognition on low-power portable devices running on microcontrollers. The ESP-32© CAM microcontroller was used as the target device, on which an artificial neural network was deployed, written using the Python® programming language and the Tensorflow© library for building neural networks. The performance of the microcontroller and personal computer for object detection using a neural network and their classification were compared in the paper. The image recognition time and percentage of correctly classified objects were compared. The paper shows that the number of training epochs affects the accuracy of object classification in the image. The obtained results show that increasing the number of training epochs increases the accuracy of object recognition using the studied neural network, but a significant increase in the number of epochs does not lead to a significant improvement in recognition accuracy. The difference in the obtained results for the microcontroller and personal computer image recognition accuracy ranges from 5%. http://elc.kpi.ua/article/view/277487microcontrollerneural networkepochtrainingclassification |
spellingShingle | Rostyslav Dmytrovych Sharuiev Pavlo Vasylovych Popovych Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller Mìkrosistemi, Elektronìka ta Akustika microcontroller neural network epoch training classification |
title | Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller |
title_full | Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller |
title_fullStr | Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller |
title_full_unstemmed | Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller |
title_short | Research of the Characteristics of a Convolutional Neural Network on the ESP32-CAM Microcontroller |
title_sort | research of the characteristics of a convolutional neural network on the esp32 cam microcontroller |
topic | microcontroller neural network epoch training classification |
url | http://elc.kpi.ua/article/view/277487 |
work_keys_str_mv | AT rostyslavdmytrovychsharuiev researchofthecharacteristicsofaconvolutionalneuralnetworkontheesp32cammicrocontroller AT pavlovasylovychpopovych researchofthecharacteristicsofaconvolutionalneuralnetworkontheesp32cammicrocontroller |