EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Classification of soybean seeds based on RGB reconstruction of hyperspectral images

Xu Yang, Kejia Ma, Dejia Zhang, Shaozhong Song iD, Xiaofeng An

PLOS ONE · 04.09.2024 · 19 (9) · e0307329

DOI: 10.1371/journal.pone.0307329 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 04.09.2024. Verfasst von Xu Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China. Hauptthemen laut MEDLINE: Glycine max, Seeds, Hyperspectral Imaging. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jilin Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soyabean is an incredibly significant component of Chinese agricultural product, and categorizing soyabean seeds allows for a better understanding of the features, attributes, and applications of many species of soyabean. This enables farmers to choose appropriate seeds for sowing in order to increase production and quality. As a result, this thesis provides a method for classifying soybean seeds that uses hyperspectral RGB picture reconstruction. Firstly, hyperspectral images of seven varieties of soybean, H1, H2, H3, H4, H5, H6 and H7, were collected by hyperspectral imager, and by using the principle of the three base colours, the R, G and B bands which have more characteristic information are selected to reconstruct the images with different texture and colour characteristics to generate a new dataset for seed segmentation, and finally, a comparison is made with the classification effect of the seven models. The experimental results in ResNet34 show that the classification accuracy of the dataset before and after RGB reconstruction increases from 88.87% to 91.75%, demonstrating that RGB image reconstruction can strengthen image features; ResNet18, ResNet34, ResNet50, ResNet101, CBAM-ResNet34, SENet-ResNet34, and SENet-ResNet34-DCN models have classification accuracies of 72.25%, 91.75%, 89%, 88.48%, 92.28%, 92.80%, and 94.24%, respectively.SENet-ResNet34-DCN achieves the greatest classification accuracy results, with a model loss of roughly 0.3. The proposed SENet-ResNet34-DCN model is the most effective at classifying soybean seeds. By classifying and optimally selecting seed varieties, agricultural production can become more scientific, efficient, and sustainable, resulting in higher returns for farmers and contributing to global food security and sustainable development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Glycine maxSeedsHyperspectral ImagingImage Processing, Computer-AssistedColor

Autor:innen und Institutionen

  • College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China.
  • Jilin Engineering Normal University, Changchun, China.

ORCID-Profile: Shaozhong Song

Förderung

  • Natural Science Foundation of Jilin Province

Zitieren

APA

Yang, X., Ma, K., Zhang, D., Song, S., & An, X. (2024). Classification of soybean seeds based on RGB reconstruction of hyperspectral images. PLOS ONE, 19(9), e0307329. https://doi.org/10.1371/journal.pone.0307329

Vancouver

Yang X, Ma K, Zhang D, Song S, An X. Classification of soybean seeds based on RGB reconstruction of hyperspectral images. PLOS ONE. 2024;19(9):e0307329. doi:10.1371/journal.pone.0307329

BibTeX
@article{Yang2024,
  author = {Yang, Xu and Ma, Kejia and Zhang, Dejia and Song, Shaozhong and An, Xiaofeng},
  title = {Classification of soybean seeds based on RGB reconstruction of hyperspectral images},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {9},
  pages = {e0307329},
  doi = {10.1371/journal.pone.0307329}
}
Kostenlos starten →