Cover Image

Fruit ripeness classification with few-shot learning

Deep learning based image classification systems require large amount of training data and long training time. However, the availability of large annotated image dataset is usually limited and expensive to generate, which limits a vision system to adapt to new task efficiently. In this paper, a few-...

Full description

Saved in:
Bibliographic Details
Main Authors: Ng, Hui-Fuang, Lo, Jie-Jin, Lin, Chih-Yang, Tan, Hung-Khoon, Chuah, Joon-Huang, Leung, Kar-Hang
Format: Article
Published: Springer Science 2022
Subjects:
SB Plant culture
Online Access:http://eprints.um.edu.my/43257/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125245558&doi=10.1007%2f978-981-16-8129-5_109&partnerID=40&md5=73bacfd3560434828a149f876fc6987f
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.43257
record_format eprints
spelling my.um.eprints.432572023-12-03T01:59:50Z http://eprints.um.edu.my/43257/ Fruit ripeness classification with few-shot learning Ng, Hui-Fuang Lo, Jie-Jin Lin, Chih-Yang Tan, Hung-Khoon Chuah, Joon-Huang Leung, Kar-Hang SB Plant culture Deep learning based image classification systems require large amount of training data and long training time. However, the availability of large annotated image dataset is usually limited and expensive to generate, which limits a vision system to adapt to new task efficiently. In this paper, a few-shot classification framework is proposed which can adapt one fruit ripeness classification system to classify new types of fruits using only a few training samples. The proposed framework adopts the meta-learning paradigm where a base network learns to extract meta-features and few-shot classification tasks from the base classes with abundant training samples and then apply the network to similar task on the novel classes using only a few support samples. Experimental results indicate that the proposed framework is able to achieve over 75 ripeness classification accuracy on various fruits using a little as five samples. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. Springer Science 2022 Article PeerReviewed Ng, Hui-Fuang and Lo, Jie-Jin and Lin, Chih-Yang and Tan, Hung-Khoon and Chuah, Joon-Huang and Leung, Kar-Hang (2022) Fruit ripeness classification with few-shot learning. Lecture Notes in Electrical Engineering, 829 LN. 715 – 720. ISSN 1876-1100, DOI https://doi.org/10.1007/978-981-16-8129-5_109 <https://doi.org/10.1007/978-981-16-8129-5_109>. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125245558&doi=10.1007%2f978-981-16-8129-5_109&partnerID=40&md5=73bacfd3560434828a149f876fc6987f 10.1007/978-981-16-8129-5_109
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic SB Plant culture
spellingShingle SB Plant culture
Ng, Hui-Fuang
Lo, Jie-Jin
Lin, Chih-Yang
Tan, Hung-Khoon
Chuah, Joon-Huang
Leung, Kar-Hang
Fruit ripeness classification with few-shot learning
description Deep learning based image classification systems require large amount of training data and long training time. However, the availability of large annotated image dataset is usually limited and expensive to generate, which limits a vision system to adapt to new task efficiently. In this paper, a few-shot classification framework is proposed which can adapt one fruit ripeness classification system to classify new types of fruits using only a few training samples. The proposed framework adopts the meta-learning paradigm where a base network learns to extract meta-features and few-shot classification tasks from the base classes with abundant training samples and then apply the network to similar task on the novel classes using only a few support samples. Experimental results indicate that the proposed framework is able to achieve over 75 ripeness classification accuracy on various fruits using a little as five samples. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
format Article
author Ng, Hui-Fuang
Lo, Jie-Jin
Lin, Chih-Yang
Tan, Hung-Khoon
Chuah, Joon-Huang
Leung, Kar-Hang
author_facet Ng, Hui-Fuang
Lo, Jie-Jin
Lin, Chih-Yang
Tan, Hung-Khoon
Chuah, Joon-Huang
Leung, Kar-Hang
author_sort Ng, Hui-Fuang
title Fruit ripeness classification with few-shot learning
title_short Fruit ripeness classification with few-shot learning
title_full Fruit ripeness classification with few-shot learning
title_fullStr Fruit ripeness classification with few-shot learning
title_full_unstemmed Fruit ripeness classification with few-shot learning
title_sort fruit ripeness classification with few-shot learning
publisher Springer Science
publishDate 2022
url http://eprints.um.edu.my/43257/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125245558&doi=10.1007%2f978-981-16-8129-5_109&partnerID=40&md5=73bacfd3560434828a149f876fc6987f
_version_ 1784586072594841600
score 13.211869

Similar Items