EUVIMEDEUVIMED entdecken
Crossref

Abnormal phenotypic defects detection of jujube using explainable machine learning enhanced computer vision

Luwei Zhang, Yan Chen, Xiangyun Guo, You Li, Chao Chen, Yu Zou, Xiaoshuan Zhang, Jinyou Hu iD

Journal of Food Science · 2024

DOI: 10.1111/1750-3841.17393 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Food Science, 2024. Verfasst von Luwei Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering, China Agricultural University, Beijing, China. Hauptthemen laut MEDLINE: Ziziphus, Machine Learning, Phenotype, Fruit. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Research and Application of Artificial Intelligence-Based Grading for Agricultural Product Commercialization.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Jujube is susceptible to biotic and abiotic adversity stresses resulting in abnormal phenotypic defects. Therefore, abnormal phenotype fruits should be removed during postharvest sorting to increase added value. An improved maximum horizontal diameter linear regression (MHD‐LR) method for size grading of jujube prior to detection of abnormal phenotypic defects was developed. The accuracy of the MHD‐LR model is 95%, with an error of only 0.95 mm. In addition, a method for detecting abnormal phenotypic defects in jujube was established. It can effectively and accurately classify seven kinds of jujube phenotypes (regular, irregular, wrinkled, moldy, hole‐broken, skin‐broken, and scarred). The data augmentation method based on linear interpolation can effectively expand the dataset with a variance of only 0.0006. Support vector machine‐decision tree (SVMDT), logistic regression, back propagation neural network, and long short‐term memory network models were established to classify jujube samples with different phenotypes, with accuracies of 99.57%, 99.00%, 99.14%, and 99.29%, respectively. The results showed that the SVMDT model had higher accuracy and explainability. This research is expected to provide a new method to improve the precise classification of abnormal phenotypic defects in postharvest jujube.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ZiziphusMachine LearningPhenotypeFruitSupport Vector MachineNeural Networks, ComputerLogistic Models

Stichwörter der Autor:innen

abnormal phenotypic defectscomputer visionexplainable machine learningimage processing

Autor:innen und Institutionen

  • College of Engineering, China Agricultural University, Beijing, China.
  • Beijing Key Laboratory of Growth and Developmental Regulation for Protected Vegetable Crops, Department of Vegetable Science, College of Horticulture, China Agricultural University, Beijing, China.
  • School of Information Management, Beijing Information Science & Technology University, Beijing, China.
  • Shanghai Herong Agribusiness Development Limited Co., Ltd., Shanghai, China.

ORCID-Profile: Jinyou Hu

Förderung

  • Research and Application of Artificial Intelligence-Based Grading for Agricultural Product Commercialization

Zitieren

APA

Zhang, L., Chen, Y., Guo, X., Li, Y., Chen, C., Zou, Y., Zhang, X., & Hu, J. (2024). Abnormal phenotypic defects detection of jujube using explainable machine learning enhanced computer vision. Journal of Food Science. https://doi.org/10.1111/1750-3841.17393

Vancouver

Zhang L, Chen Y, Guo X, Li Y, Chen C, Zou Y, et al. Abnormal phenotypic defects detection of jujube using explainable machine learning enhanced computer vision. Journal of Food Science. 2024. doi:10.1111/1750-3841.17393

BibTeX
@article{Zhang2024,
  author = {Zhang, Luwei and Chen, Yan and Guo, Xiangyun and Li, You and Chen, Chao and Zou, Yu and Zhang, Xiaoshuan and Hu, Jinyou},
  title = {Abnormal phenotypic defects detection of jujube using explainable machine learning enhanced computer vision},
  journal = {Journal of Food Science},
  year = {2024},
  doi = {10.1111/1750-3841.17393}
}
Kostenlos starten →