Fruit freshness detection based on multi-task convolutional neural network
Current Research in Food Science · 2024 · 8 · 100733
DOI: 10.1016/j.crfs.2024.100733 ↗Kurz gefasst
Fachartikel in der Zeitschrift Current Research in Food Science, 2024. Verfasst von Yinsheng Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang Food and Drug Quality & Safety Engineering Research Institute, Zhejiang Gongshang University, Hangzhou, 310018, China. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Ministry of Science and Technology of the People's Republic of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Background
Fruit freshness detection by computer vision is essential for many agricultural applications, e.g., automatic harvesting and supply chain monitoring. This paper proposes to use the multi-task learning (MTL) paradigm to build a deep convolutional neural work for fruit freshness detection.
Results
We design an MTL model that optimizes the freshness detection (T1) and fruit type classification (T2) tasks in parallel. The model uses a shared CNN (convolutional neural network) subnet and two FC (fully connected) task heads. The shared CNN acts as a feature extraction module and feeds the two task heads with common semantic features. Based on an open fruit image dataset, we conducted a comparative study of MTL and single-task learning (STL) paradigms. The STL models use the same CNN subnet with only one specific task head. In the MTL scenario, the T1 and T2 mean accuracies on the test set are 93.24% and 88.66%, respectively. Meanwhile, for STL, the two accuracies are 92.50% and 87.22%. Statistical tests report significant differences between MTL and STL on T1 and T2 test accuracies. We further investigated the extracted feature vectors (semantic embeddings) from the two STL models. The vectors have an averaged 0.7 cosine similarity on the entire dataset, with most values lying in the 0.6-0.8 range. This indicates a between-task correlation and justifies the effectiveness of the proposed MTL approach.
Conclusion
This study proves that MTL exploits the mutual correlation between two or more relevant tasks and can maximally share their underlying feature extraction process. we envision this approach to be extended to other domains that involve multiple interconnected tasks.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Zhejiang Food and Drug Quality & Safety Engineering Research Institute, Zhejiang Gongshang University, Hangzhou, 310018, China.
- School of Management and E-Business, Zhejiang Gongshang University, Hangzhou, 310018, China.
- School of Management Science and Engineering, Nanjing University of Finance and Economics, Nanjing, 210023, China.
- Institute of Science and Technology, Jiangnan University, Wuxi, 214122, China.
- School of Food Science and Technology, Jiangnan University, Wuxi, 214122, China.
Förderung
- Ministry of Science and Technology of the People's Republic of China
- National Natural Science Foundation of China
Zitieren
APA
Zhang, Y., Yang, X., Cheng, Y., Wu, X., Sun, X., Hou, R., & Wang, H. (2024). Fruit freshness detection based on multi-task convolutional neural network. Current Research in Food Science, 8, 100733. https://doi.org/10.1016/j.crfs.2024.100733
Vancouver
Zhang Y, Yang X, Cheng Y, Wu X, Sun X, Hou R, et al. Fruit freshness detection based on multi-task convolutional neural network. Current Research in Food Science. 2024;8:100733. doi:10.1016/j.crfs.2024.100733
BibTeX
@article{Zhang2024,
author = {Zhang, Yinsheng and Yang, Xudong and Cheng, Yongbo and Wu, Xiaojun and Sun, Xiulan and Hou, Ruiqi and Wang, Haiyan},
title = {Fruit freshness detection based on multi-task convolutional neural network},
journal = {Current Research in Food Science},
year = {2024},
volume = {8},
pages = {100733},
doi = {10.1016/j.crfs.2024.100733}
}
EUVIMED