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

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Wang, Ziyan Shi, Kaiyao Hou, Ning Yan, Cuiyun Wu, Xu Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155035627880448
author Qi Wang
Ziyan Shi
Kaiyao Hou
Ning Yan
Cuiyun Wu
Xu Li
author_facet Qi Wang
Ziyan Shi
Kaiyao Hou
Ning Yan
Cuiyun Wu
Xu Li
author_sort Qi Wang
collection DOAJ
description 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 R<sup>2</sup> 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.
format Article
id doaj-art-750a97cbf0bc45cabba7bef926085c9e
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-750a97cbf0bc45cabba7bef926085c9e2025-08-20T02:25:04ZengMDPI AGSensors1424-82202025-04-01258254510.3390/s25082545Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid ModelingQi Wang0Ziyan Shi1Kaiyao Hou2Ning Yan3Cuiyun Wu4Xu Li5College of Information Engineering, Tarim University, Alaer 843300, ChinaCollege of Information Engineering, Tarim University, Alaer 843300, ChinaCollege of Information Engineering, Tarim University, Alaer 843300, ChinaCollege of Information Engineering, Tarim University, Alaer 843300, ChinaCollege of Information Engineering, Tarim University, Alaer 843300, ChinaCollege of Information Engineering, Tarim University, Alaer 843300, ChinaChlorophyll 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 R<sup>2</sup> 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.https://www.mdpi.com/1424-8220/25/8/2545chlorophyll contentjujube leavessmartphone imagesSPADprecision agriculture
spellingShingle Qi Wang
Ziyan Shi
Kaiyao Hou
Ning Yan
Cuiyun Wu
Xu Li
Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling
Sensors
chlorophyll content
jujube leaves
smartphone images
SPAD
precision agriculture
title Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling
title_full Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling
title_fullStr Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling
title_full_unstemmed Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling
title_short Smartphone-Based SPAD Value Estimation for Jujube Leaves Using Machine Learning: A Study on RGB Feature Extraction and Hybrid Modeling
title_sort smartphone based spad value estimation for jujube leaves using machine learning a study on rgb feature extraction and hybrid modeling
topic chlorophyll content
jujube leaves
smartphone images
SPAD
precision agriculture
url https://www.mdpi.com/1424-8220/25/8/2545
work_keys_str_mv AT qiwang smartphonebasedspadvalueestimationforjujubeleavesusingmachinelearningastudyonrgbfeatureextractionandhybridmodeling
AT ziyanshi smartphonebasedspadvalueestimationforjujubeleavesusingmachinelearningastudyonrgbfeatureextractionandhybridmodeling
AT kaiyaohou smartphonebasedspadvalueestimationforjujubeleavesusingmachinelearningastudyonrgbfeatureextractionandhybridmodeling
AT ningyan smartphonebasedspadvalueestimationforjujubeleavesusingmachinelearningastudyonrgbfeatureextractionandhybridmodeling
AT cuiyunwu smartphonebasedspadvalueestimationforjujubeleavesusingmachinelearningastudyonrgbfeatureextractionandhybridmodeling
AT xuli smartphonebasedspadvalueestimationforjujubeleavesusingmachinelearningastudyonrgbfeatureextractionandhybridmodeling