A fruits recognition system based on a modern deep learning technique; Journal of Physics: Conference Series; Vol. 1327 : Innovations in Non-Destructive Testing (SibTest 2019)

A fruits recognition system based on a modern deep learning technique; Journal of Physics: Conference Series; Vol. 1327 : Innovations in Non-Destructive Testing (SibTest 2019)

Bibliographic Details
Parent link:Journal of Physics: Conference Series
Vol. 1327 : Innovations in Non-Destructive Testing (SibTest 2019).— 2019.— [012050, 5 р.]
Main Author: Dang Thi Phuong Chung
Corporate Author: Томский политехнический университет
Other Authors: Dinh Van Tai
Summary:Title screen
The popular technology used in this innovative era is Computer vision for fruit recognition. Compared to other machine learning (ML) algorithms, deep neural networks (DNN) provide promising results to identify fruits in images. Currently, to identify fruits, different DNN-based classification algorithms are used. However, the issue in recognizing fruits has yet to be addressed due to similarities in size, shape and other features. This paper briefly discusses the use of deep learning (DL) for recognizing fruits and its other applications. The paper will also provide a concise explanation of convolution neural networks (CNNs) and the EfficientNet architecture to recognize fruit using the Fruit 360 dataset. The results show that the proposed model is 95% more accurate.
Language:English
Published: 2019
Subjects:
электронный ресурс
труды учёных ТПУ
системы распознавания
фрукты
компьютерное зрение
алгоритмы
машинное обучение
идентификация
изображения
нейронные сети
сверточные нейронные сети
Online Access:https://doi.org/10.1088/1742-6596/1327/1/012050
http://earchive.tpu.ru/handle/11683/57042
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=661313

Similar Items

Similar Items