Please use this identifier to cite or link to this item:
https://elib.vku.udn.vn/handle/123456789/3178
Title: | Intelligent Fruit Recognition System Using Deep Learning |
Authors: | Nguyen, Ha Huy Cuong Luong, Anh Tuan Trinh, Trung Hai Ho, Phan Hieu Meesad, Phayung Nguyen, Thanh Thuy |
Keywords: | Fruit recognition Computer vision Image processing Image classification Convolution Neural Network |
Issue Date: | Jun-2021 |
Publisher: | Springer Nature |
Abstract: | Industrial Revolution 4.0 has made us people more professional, automating all production stages from office work to project work on farms. In the precision agriculture, it is very urgent to bring new and effective solutions to using artificial intelligence for people to use and improve the manual steps gradually, and increase the automation feature. So, automatic fruit recognition technique is the latest trend and effective technique in precision agriculture. This paper proposes a technical solution for fruit classification using deep learning. Automatic fruit identification using computer vision is considered a challenging task. This is because there are similarities between fruits and changes in the external environment such as light affect the fruit recognition model. Most previously implemented techniques have some limitations since their testing and evaluation is done using a limited set of data sets. Some implementations, does not consider changes to the external environment for the image are considered in this implementation. In this paper, exploring part of the deep learning algorithms was achieved and discovered strengths and weaknesses for these algorithms. The knowledge was gained on deep learning and a model was built that could recognize fruits from images. |
Description: | International Conference on Computing and Information Technology (IC2IT 2021); Lecture Notes in Networks and Systems book series, Vol 251; pp: 13–22. |
URI: | http://elib.vku.udn.vn/handle/123456789/3178 https://link.springer.com/chapter/10.1007/978-3-030-79757-7_2 |
ISBN: | 978-3-030-79756-0 |
Appears in Collections: | NĂM 2021 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.