Fruit Ripeness Classification with Few-Shot Learning

Hui Fuang Ng, Jie Jin Lo, Chih Yang Lin, Hung Khoon Tan, Joon Huang Chuah, Kar Hang Leung

研究成果: 書貢獻/報告類型會議論文篇章同行評審

2 引文 斯高帕斯(Scopus)

摘要

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.

原文???core.languages.en_GB???
主出版物標題Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications - Enhancing Research and Innovation through the Fourth Industrial Revolution
編輯Nor Muzlifah Mahyuddin, Nor Rizuan Mat Noor, Harsa Amylia Mat Sakim
發行者Springer Science and Business Media Deutschland GmbH
頁面715-720
頁數6
ISBN(列印)9789811681288
DOIs
出版狀態已出版 - 2022
事件11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021 - Virtual, Online
持續時間: 5 4月 20216 4月 2021

出版系列

名字Lecture Notes in Electrical Engineering
829 LNEE
ISSN(列印)1876-1100
ISSN(電子)1876-1119

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021
城市Virtual, Online
期間5/04/216/04/21

指紋

深入研究「Fruit Ripeness Classification with Few-Shot Learning」主題。共同形成了獨特的指紋。

引用此