Fruit ripeness classification with few-shot learning
Document Type
Article
Publication Date
1-1-2022
Abstract
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.
Keywords
Deep learning, Fruits, Image classification, Large dataset, Sampling, Deep learning, Few-shot learning, Fruit ripeness, Image classification systems, Image datasets, Large amounts, Shot classification, Training data, Training sample, Training time, Classification (of information)
Divisions
sch_ecs
Funders
None
Publication Title
Lecture Notes in Electrical Engineering
Volume
829 LN
Publisher
Springer Science
Additional Information
Cited by: 2; Conference name: 11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021; Conference date: 5 April 2021 through 6 April 2021; Conference code: 272139