EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling

Qi Wang iD, Ziyan Shi, Kaiyao Hou, Ning Yan iD, Cuiyun Wu, Xu Li

Sensors · 2025

DOI: 10.3390/s25082545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Qi Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Tarim University, Alaer 843300, China. Hauptthemen laut MEDLINE: Smartphone, Plant Leaves, Machine Learning, Ziziphus. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Oasis Ecological Agriculture Corps Key Laboratory Open Project, the Corps Science and Technology Program, the Tarim University Innovation Team Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chlorophyll content in date leaves is critical for fruit quality and yield. Traditional detection methods are usually complex and expensive. This study proposes a rapid detection method for chlorophyll content using smartphone images and machine learning and deep learning models. The SPAD values and RGB images of Xinjiang date palm were collected. The RGB images were preprocessed and their color features were extracted using Python and OpenCV. Through correlation analysis, 21 color features highly correlated with chlorophyll content were selected and downscaled with principal component analysis. Models including SVR, RVM, CNN, CNN-SVR, and CNN-RVM were used for prediction. Among them, the CNN-SVR model showed the most stable performance with R2 values of 72.21% and 77.44% on the training and validation sets, respectively, which outperformed the other models. The proposed method is simple, cost-effective, and highly accurate, providing a novel technical approach for accurate management and health monitoring in the date industry. This method has the potential for wide application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SmartphonePlant LeavesMachine LearningZiziphusChlorophyllPrincipal Component AnalysisDeep LearningNeural Networks, ComputerColorImage Processing, Computer-Assisted

Stichwörter der Autor:innen

SPADchlorophyll contentjujube leavesprecision agriculturesmartphone images

Substanzen

Chlorophyll

Autor:innen und Institutionen

  • College of Information Engineering, Tarim University, Alaer 843300, China.
  • Key Laboratory of Tarim Oasis Agriculture, Ministry of Education, Tarim University, Alaer 843300, China.

ORCID-Profile: Qi Wang, Ning Yan

Förderung

  • the Oasis Ecological Agriculture Corps Key Laboratory Open Project
  • the Corps Science and Technology Program
  • the Tarim University Innovation Team Project
  • the National Natural Science Foundation of China
  • the China Agricultural University-Tarim University Joint Scientific Research Fund
  • the 2024 Aral Science and Technology Program Project-Development and Application of Apple Picking Robots Based on Artificial Intelligence
  • the Corps Science and Technology Program Project-Breeding of New Early-Maturing, High-Quality, Large-Fruit, and Fresh-Consumption Jujube Varieties (Jin Mi Cui…
  • Oasis Ecological Agriculture Corps Key Laboratory Open Project

Zitieren

APA

Wang, Q., Shi, Z., Hou, K., Yan, N., Wu, C., & Li, X. (2025). Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling. Sensors. https://doi.org/10.3390/s25082545

Vancouver

Wang Q, Shi Z, Hou K, Yan N, Wu C, Li X. Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling. Sensors. 2025. doi:10.3390/s25082545

BibTeX
@article{Wang2025,
  author = {Wang, Qi and Shi, Ziyan and Hou, Kaiyao and Yan, Ning and Wu, Cuiyun and Li, Xu},
  title = {Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25082545}
}
Kostenlos starten →