Vegetable and fruit freshness detection based on deep features and principal component analysis
Current Research in Food Science · 2024 · 8 · 100656
DOI: 10.1016/j.crfs.2023.100656 ↗Kurz gefasst
Fachartikel in der Zeitschrift Current Research in Food Science, 2024. Verfasst von Yue Yuan und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Shenyang University, Shenyang, 110042, China. Die Arbeit wurde bisher 69-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Vegetable and fruit freshness detecting can ensure that consumers get vegetables and fruits with good taste and rich nutrition, improve the health level of diet, and ensure that the agricultural and food industries provide high-quality products to meet consumer needs and increase sales and market share. At present, the freshness detection of vegetables and fruits mainly relies on manual observation and judgment, which has the problems of subjectivity and low accuracy, and it is difficult to meet the needs of large-scale, high-efficiency, and rapid detection. Although some studies have shown that large-scale detection of vegetable and fruit freshness can be carried out based on artificially extracted features, there is still the problem of poor adaptability of artificially extracted features, which leads to low efficiency of freshness detection. To solve this problem, this paper proposes a novel method for detecting the freshness of vegetables and fruits more objectively, accurately and efficiently using deep features extracted by pre-trained deep learning models of different architectures. First, resized images of vegetables and fruits are fed into a pre-trained deep learning model for deep feature extraction. Then, the deep features are fused and the fused deep features are dimensionally reduced to a representative low-dimensional feature space by principal component analysis. Finally, vegetable and fruit freshness are detected by three machine learning methods. The experimental results show that combining the deep features extracted by the three architecture pre-trained deep learning models GoogLeNet, DenseNet-201 and ResNeXt-101 combined with PCA dimensionality reduction processing has achieved the highest accuracy rate of 96.98% for vegetable and fruit freshness detection. This research concluded that the proposed method is promising to improve the efficiency of freshness detection of vegetables and fruits.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Shenyang University, Shenyang, 110042, China.
- Liaoning Provincial Public Security Department, Shenyang, 110000, China.
Zitieren
APA
Yuan, Y., & Chen, X. (2024). Vegetable and fruit freshness detection based on deep features and principal component analysis. Current Research in Food Science, 8, 100656. https://doi.org/10.1016/j.crfs.2023.100656
Vancouver
Yuan Y, Chen X. Vegetable and fruit freshness detection based on deep features and principal component analysis. Current Research in Food Science. 2024;8:100656. doi:10.1016/j.crfs.2023.100656
BibTeX
@article{Yuan2024,
author = {Yuan, Yue and Chen, Xianlong},
title = {Vegetable and fruit freshness detection based on deep features and principal component analysis},
journal = {Current Research in Food Science},
year = {2024},
volume = {8},
pages = {100656},
doi = {10.1016/j.crfs.2023.100656}
}
EUVIMED