Publication: Determination of Fruit Quality by Image Using Deep Neural Network
Дата
2022
Авторы
Snatkina, O. A.
Kugushev, A. R.
Journal Title
Journal ISSN
Volume Title
Издатель
Аннотация
© 2022 IEEE.This paper proposes an approach to recognizing and determining the freshness of fruits based on the YOLOv3 neural network, working with both images and videos. 6 classes are used as recognition objects: fresh and spoiled bananas, oranges, and apples. To train the network, its own marked-up dataset is used. A small amount of training data is enough for the network to show good quality metrics and correct work results. The precision of recognition and determination of fruit freshness was 90%, recall 96%.
Описание
Ключевые слова
Цитирование
Snatkina, O. A. Determination of Fruit Quality by Image Using Deep Neural Network / Snatkina, O.A., Kugushev, A.R. // Proceedings of the 2022 Conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2022. - 2022. - P. 1423-1426. - 10.1109/ElConRus54750.2022.9755693